Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

notes on my reinforcement learning for rocket league side quest so far: i’m in awe that — we live in a time where i can train a reinforcement learning model that is learning to play rocket league and at the same time, test community made rocket league models. where,...

naklecha's profile picture

naklecha

16,596 subscribers

46,302 Aufrufe • vor 1 Jahr •via X (Twitter)

GamingWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Joseph Suarez (e/🐡)
Joseph Suarez (e/🐡)vor 1 Jahr

Hi - can pufferlib help? We have the fastest, lowest overhead CPU vectorization and some nice hyperparam sweeps tools, plus nice compatibility layers

Profilbild von naklecha
naklechavor 1 Jahr

heyy thankss, ill check it out!!

Profilbild von Anindya
Anindyavor 1 Jahr

Just curious, how are you connecting your env with your code? Like is it just for this game or is there any sort of package?

Profilbild von naklecha
naklechavor 1 Jahr

rocket leagues has a bunch of tooling built out for bots and the community built out a client that cab handle code and game connections and stuff

Profilbild von dazai
dazaivor 1 Jahr

what's the performance of the rl model?

Profilbild von naklecha
naklechavor 1 Jahr

its an example script, still have to write some more code for my model to be used in the game (but it looks straightforward). i have some work to do right now, i'll prob try and make it work at night when i'm free.

Profilbild von Kai
Kaivor 1 Jahr

goated stuff

Profilbild von Binguin
Binguinvor 1 Jahr

may I ask what your hardware is?

Profilbild von naklecha
naklechavor 1 Jahr

its a 4090

Profilbild von Farhaj Mayan
Farhaj Mayanvor 1 Jahr

@aarondegods rocket league x ai agents - your dream come true

Profilbild von naklecha
naklechavor 1 Jahr

@aarondegods farhaj hiiii

Ähnliche Videos

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!
53:45

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

RoboPapers

38,334 Aufrufe • vor 1 Monat

In order for robots to be deployed in the real world, performing tasks of real value, they must be reliable. Unfortunately, even more, most robotic demos work maybe 70-80% of the time at best. The way to get better reliability is to do real-world reinforcement learning: having the robot teach itself how to perform the task up to a high level of success. The key to doing this is to start with a core of expert human data, use that to train a policy then iteratively improve it, until finally finishing with on-policy reinforcement learning. Kun Lei talks through a unified framework for imitation and reinforcement learning based on PPO, which enables this improvement process. In this episode, Kun Lei explains the theory behind his reinforcement learning method and how it allowed his robot to run in a shopping mall juicing oranges for seven hours at a time, among experiments on a wide variety of tasks and embodiments. Watch episode 58 of RoboPapers now, hosted by Michael Cho - Rbt/Acc and Chris Paxton!
1:11:51

In order for robots to be deployed in the real world, performing tasks of real value, they must be reliable. Unfortunately, even more, most robotic demos work maybe 70-80% of the time at best. The way to get better reliability is to do real-world reinforcement learning: having the robot teach itself how to perform the task up to a high level of success. The key to doing this is to start with a core of expert human data, use that to train a policy then iteratively improve it, until finally finishing with on-policy reinforcement learning. Kun Lei talks through a unified framework for imitation and reinforcement learning based on PPO, which enables this improvement process. In this episode, Kun Lei explains the theory behind his reinforcement learning method and how it allowed his robot to run in a shopping mall juicing oranges for seven hours at a time, among experiments on a wide variety of tasks and embodiments. Watch episode 58 of RoboPapers now, hosted by Michael Cho - Rbt/Acc and Chris Paxton!

RoboPapers

18,813 Aufrufe • vor 6 Monaten

Everybody is talking about recursive self-improvement (RSI) and meta learning. Here is my old 2020 talk about this [1]. It has aged well. Example: humans still define the starts & ends of trials of many modern meta learners. My RSI systems since 1994 LEARN to (re)define them [2]! [1] Meta Learning Machines in a Single Lifelong Trial (talk for workshops at ICML 2020 and NeurIPS 2021, based on earlier talks since 1994). Abstract: the most widely used machine learning algorithms were designed by humans and thus are hindered by our cognitive biases and limitations. Can we also construct meta learning algorithms that can learn better learning algorithms so that our self-improving AIs have no limits other than those inherited from computability and physics? This question has been a main driver of my research since I wrote a thesis on it in 1987 [2]. Here I summarize our work on meta reinforcement learning with self-modifying policies in a single lifelong trial (since 1994), and mathematically optimal meta-learning through the self-referential Gödel Machine (since 2003). Many additional publications on meta-learning since 1987 can be found in the RSI overview [2]. [2] J. Schmidhuber (AI Blog, 2020-2025). 1/3 century anniversary of first publication on recursive self-improvement (RSI) and meta learning machines that learn to learn (1987). For its cover I drew a robot that bootstraps itself. 1992-: gradient descent-based neural meta learning. 1994-: meta reinforcement learning with self-modifying policies. 1997: meta RL plus artificial curiosity and intrinsic motivation. 2002-: asymptotically optimal meta learning for curriculum learning. 2003-: mathematically optimal Gödel Machine. 2020-: new stuff!
23:42

Everybody is talking about recursive self-improvement (RSI) and meta learning. Here is my old 2020 talk about this [1]. It has aged well. Example: humans still define the starts & ends of trials of many modern meta learners. My RSI systems since 1994 LEARN to (re)define them [2]! [1] Meta Learning Machines in a Single Lifelong Trial (talk for workshops at ICML 2020 and NeurIPS 2021, based on earlier talks since 1994). Abstract: the most widely used machine learning algorithms were designed by humans and thus are hindered by our cognitive biases and limitations. Can we also construct meta learning algorithms that can learn better learning algorithms so that our self-improving AIs have no limits other than those inherited from computability and physics? This question has been a main driver of my research since I wrote a thesis on it in 1987 [2]. Here I summarize our work on meta reinforcement learning with self-modifying policies in a single lifelong trial (since 1994), and mathematically optimal meta-learning through the self-referential Gödel Machine (since 2003). Many additional publications on meta-learning since 1987 can be found in the RSI overview [2]. [2] J. Schmidhuber (AI Blog, 2020-2025). 1/3 century anniversary of first publication on recursive self-improvement (RSI) and meta learning machines that learn to learn (1987). For its cover I drew a robot that bootstraps itself. 1992-: gradient descent-based neural meta learning. 1994-: meta reinforcement learning with self-modifying policies. 1997: meta RL plus artificial curiosity and intrinsic motivation. 2002-: asymptotically optimal meta learning for curriculum learning. 2003-: mathematically optimal Gödel Machine. 2020-: new stuff!

Jürgen Schmidhuber

222,940 Aufrufe • vor 4 Monaten

OpenAI's Kevin Weil 🇺🇸 says 24/7 robotic labs could automate scientific discovery using "reinforcement learning with a loop through the real world": "There’s a lot of science that can be totally automated. There’s no reason at this point that you need to have grad students pipetting one thing into another thing." "The idea is to have robotic labs that are online 24/7 and can scale in parallel. You have models reasoning for two days to find the most efficient experiments to run, once they get to a good point, they pass that to a robotic lab which can experiment in parallel at high volume." "The results pass back into a model which reasons about the results and then goes out and runs a different set of experiments. You’re doing reinforcement learning with a loop through the real world."
2:13

OpenAI's Kevin Weil 🇺🇸 says 24/7 robotic labs could automate scientific discovery using "reinforcement learning with a loop through the real world": "There’s a lot of science that can be totally automated. There’s no reason at this point that you need to have grad students pipetting one thing into another thing." "The idea is to have robotic labs that are online 24/7 and can scale in parallel. You have models reasoning for two days to find the most efficient experiments to run, once they get to a good point, they pass that to a robotic lab which can experiment in parallel at high volume." "The results pass back into a model which reasons about the results and then goes out and runs a different set of experiments. You’re doing reinforcement learning with a loop through the real world."

TBPN

98,711 Aufrufe • vor 5 Monaten

OpenAI's Kevin Weil 🇺🇸 says 24/7 robotic labs could automate scientific discovery using "reinforcement learning with a loop through the real world": "There’s a lot of science that can be totally automated. There’s no reason at this point that you need to have grad students pipetting one thing into another thing." "The idea is to have robotic labs that are online 24/7 and can scale in parallel. You have models reasoning for two days to find the most efficient experiments to run, once they get to a good point, they pass that to a robotic lab which can experiment in parallel at high volume." "The results pass back into a model which reasons about the results and then goes out and runs a different set of experiments. You’re doing reinforcement learning with a loop through the real world."
2:13

OpenAI's Kevin Weil 🇺🇸 says 24/7 robotic labs could automate scientific discovery using "reinforcement learning with a loop through the real world": "There’s a lot of science that can be totally automated. There’s no reason at this point that you need to have grad students pipetting one thing into another thing." "The idea is to have robotic labs that are online 24/7 and can scale in parallel. You have models reasoning for two days to find the most efficient experiments to run, once they get to a good point, they pass that to a robotic lab which can experiment in parallel at high volume." "The results pass back into a model which reasons about the results and then goes out and runs a different set of experiments. You’re doing reinforcement learning with a loop through the real world."

TBPN

29,721 Aufrufe • vor 5 Monaten

A Switzerland-based startup Flexion has created a robotic brain that helps the Unitree G1 move smoothly and work on its own. It uses reinforcement learning, where the robot trains in simulations to learn walking, balancing, and picking objects. In tests, it cleaned a space by finding and placing items in a basket without human help.
0:47

A Switzerland-based startup Flexion has created a robotic brain that helps the Unitree G1 move smoothly and work on its own. It uses reinforcement learning, where the robot trains in simulations to learn walking, balancing, and picking objects. In tests, it cleaned a space by finding and placing items in a basket without human help.

Space and Technology

17,557 Aufrufe • vor 3 Monaten

Learning robust, general-purpose reward functions for robotics unlocks many potential applications, like on-robot reinforcement learning or dataset validation. However, there’s a question of how to actually train such reward functions. Training success/failure prediction leads to ambiguous signals partway through a demonstration — it’s hard to measure progress — making the method unsuitable for reinforcement learning, among other things. Predicting progress, on the other hand, does not give a good way of using failure data. So why not do both? Robometer combines both progress and preference supervision, resulting in a stable, scalable, and highly general reward learning approach. Anthony Liang Yiğit Korkmaz and Jesse Zhang join us to tell us more. Watch Episode #84 of RoboPapers, with Chris Paxton and Jiafei Duan today!
59:14

Learning robust, general-purpose reward functions for robotics unlocks many potential applications, like on-robot reinforcement learning or dataset validation. However, there’s a question of how to actually train such reward functions. Training success/failure prediction leads to ambiguous signals partway through a demonstration — it’s hard to measure progress — making the method unsuitable for reinforcement learning, among other things. Predicting progress, on the other hand, does not give a good way of using failure data. So why not do both? Robometer combines both progress and preference supervision, resulting in a stable, scalable, and highly general reward learning approach. Anthony Liang Yiğit Korkmaz and Jesse Zhang join us to tell us more. Watch Episode #84 of RoboPapers, with Chris Paxton and Jiafei Duan today!

RoboPapers

14,363 Aufrufe • vor 1 Monat

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.
1:05

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Khurram Javed

52,110 Aufrufe • vor 7 Monaten

Today we present Morpheus, a persistent enterprise simulation platform designed to make Continual Learning a reality. Morpheus is the world’s first real world Reinforcement Learning environment. Every Reinforcement Learning environment operates in the game world. Benchmarks like Atari, OpenAI Gym, MuJoCo, and Procgen are all small, game-like worlds that reset every few minutes. But the real world never resets. A business keeps running and evolving everyday. We tested how frontier LLMs would perform in realistic and dynamic business environments 🧬on Morpheus. The main conclusion was that LLMs are not continual learners. 🧵Here’s how we did it and what we learned:
1:18

Today we present Morpheus, a persistent enterprise simulation platform designed to make Continual Learning a reality. Morpheus is the world’s first real world Reinforcement Learning environment. Every Reinforcement Learning environment operates in the game world. Benchmarks like Atari, OpenAI Gym, MuJoCo, and Procgen are all small, game-like worlds that reset every few minutes. But the real world never resets. A business keeps running and evolving everyday. We tested how frontier LLMs would perform in realistic and dynamic business environments 🧬on Morpheus. The main conclusion was that LLMs are not continual learners. 🧵Here’s how we did it and what we learned:

Skyfall AI

262,848 Aufrufe • vor 6 Tagen

These are not CGI. Reinforcement learning is so back. When operating on strings, it gives us o3. When operating on physical motors, it gives us a perfect humanoid backflip and a robot creature that out-maneuvers almost every animal on earth. RL is one of the only learning algorithms that can master both the world of bits and the world of atoms. Give me a reward function, and I shall move the world. 2025, Year of RL.
0:12

These are not CGI. Reinforcement learning is so back. When operating on strings, it gives us o3. When operating on physical motors, it gives us a perfect humanoid backflip and a robot creature that out-maneuvers almost every animal on earth. RL is one of the only learning algorithms that can master both the world of bits and the world of atoms. Give me a reward function, and I shall move the world. 2025, Year of RL.

Jim Fan

356,747 Aufrufe • vor 1 Jahr

New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn to use reinforcement learning to improve your LLM performance in this short course, built in collaboration with Predibase by Rubrik, and taught by Travis Addair, its Co-Founder and CTO, and Arnav Garg, its Senior Engineer and Machine Learning Lead. Reasoning models have been one of the most important developments in LLMs. Reinforcement Fine-Tuning (RFT) uses rewards to encourage LLMs to find solutions to multi-step reasoning tasks such as solving math problems and debugging code - without needing pre-existing training examples like in traditional supervised fine-tuning. Group Relative Policy Optimization (GRPO) is a reinforcement fine-tuning algorithm gaining rapid adoption. Developed by the DeepSeek team and used to train the R1 reasoning model, GRPO uses reward functions that you can write in Python to assign rewards to model responses. It’s beneficial for tasks with verifiable outcomes and can work well even with fewer than 100 training examples. It can also significantly improve the reasoning ability of smaller LLMs, making applications faster and more cost effective. In this course, you’ll take a technical deep dive into RFT with GRPO. You’ll learn to build reward functions that you can use in the GRPO training process to guide an LLM toward better performance on multi-step reasoning tasks. In detail, you’ll: - Learn when reinforcement fine-tuning is a better fit than supervised fine-tuning, especially for tasks involving multi-step reasoning or limited labeled data. - Understand how GRPO uses programmable reward functions as a more scalable alternative to the human feedback required for other reinforcement learning algorithms, such as RLHF and DPO. - Frame the Wordle game as a reinforcement fine-tuning problem and see how an LLM can learn to plan, analyze feedback, and improve its strategy over time. - Design reward functions that power the reinforcement fine-tuning process. - Learn techniques for evaluating more subjective tasks, such as rating the quality of a text summary, using an LLM as a judge. - Understand why reward hacking happens and how to avoid it by adding penalty functions to discourage undesirable behaviors. - Learn the four key components of the loss calculation in the GRPO algorithm: token probability distribution ratios, advantages, clipping, and KL-divergence. - Launch reinforcement fine-tuning jobs using Predibase’s hosted training services. By the end of this course, you’ll be able to build and fine-tune LLMs using reinforcement learning to improve reasoning without relying on large labeled datasets or subjective human feedback. Please sign up here:
2:41

New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn to use reinforcement learning to improve your LLM performance in this short course, built in collaboration with Predibase by Rubrik, and taught by Travis Addair, its Co-Founder and CTO, and Arnav Garg, its Senior Engineer and Machine Learning Lead. Reasoning models have been one of the most important developments in LLMs. Reinforcement Fine-Tuning (RFT) uses rewards to encourage LLMs to find solutions to multi-step reasoning tasks such as solving math problems and debugging code - without needing pre-existing training examples like in traditional supervised fine-tuning. Group Relative Policy Optimization (GRPO) is a reinforcement fine-tuning algorithm gaining rapid adoption. Developed by the DeepSeek team and used to train the R1 reasoning model, GRPO uses reward functions that you can write in Python to assign rewards to model responses. It’s beneficial for tasks with verifiable outcomes and can work well even with fewer than 100 training examples. It can also significantly improve the reasoning ability of smaller LLMs, making applications faster and more cost effective. In this course, you’ll take a technical deep dive into RFT with GRPO. You’ll learn to build reward functions that you can use in the GRPO training process to guide an LLM toward better performance on multi-step reasoning tasks. In detail, you’ll: - Learn when reinforcement fine-tuning is a better fit than supervised fine-tuning, especially for tasks involving multi-step reasoning or limited labeled data. - Understand how GRPO uses programmable reward functions as a more scalable alternative to the human feedback required for other reinforcement learning algorithms, such as RLHF and DPO. - Frame the Wordle game as a reinforcement fine-tuning problem and see how an LLM can learn to plan, analyze feedback, and improve its strategy over time. - Design reward functions that power the reinforcement fine-tuning process. - Learn techniques for evaluating more subjective tasks, such as rating the quality of a text summary, using an LLM as a judge. - Understand why reward hacking happens and how to avoid it by adding penalty functions to discourage undesirable behaviors. - Learn the four key components of the loss calculation in the GRPO algorithm: token probability distribution ratios, advantages, clipping, and KL-divergence. - Launch reinforcement fine-tuning jobs using Predibase’s hosted training services. By the end of this course, you’ll be able to build and fine-tune LLMs using reinforcement learning to improve reasoning without relying on large labeled datasets or subjective human feedback. Please sign up here:

Andrew Ng

86,457 Aufrufe • vor 1 Jahr

Many people are flat wrong about DeepSeek. You might think everyone freaked out about DeepSeek because the model is really good—which it is—or because it was from China, which is also true. But there's a more subtle reason: DeepSeek showed they could achieve those results using reinforcement learning instead of supervised fine-tuning. In other words, they didn't need an expensive phase where a bunch of people tuned the model by answering questions. They were able to do all of this faster and cheaper using reinforcement fine-tuning. This is a huge deal! I recorded the attached video with the following goals in mind: 1. Explain how reinforcement fine-tuning works 2. Show you how you can fine-tune your own models 3. Walk you through a complete code example
25:36

Many people are flat wrong about DeepSeek. You might think everyone freaked out about DeepSeek because the model is really good—which it is—or because it was from China, which is also true. But there's a more subtle reason: DeepSeek showed they could achieve those results using reinforcement learning instead of supervised fine-tuning. In other words, they didn't need an expensive phase where a bunch of people tuned the model by answering questions. They were able to do all of this faster and cheaper using reinforcement fine-tuning. This is a huge deal! I recorded the attached video with the following goals in mind: 1. Explain how reinforcement fine-tuning works 2. Show you how you can fine-tune your own models 3. Walk you through a complete code example

Santiago

105,545 Aufrufe • vor 1 Jahr

Last semester, I taught Reinforcement Learning class again at UCLA. Together with my amazing TAs Matthew and Caiyuan, we built a mini-project: MetaDrive Arena 🚗🤖 Students applied what they learned in class, trained RL agents, and competed on a live leaderboard. The results were incredible, with 94 agents, 2K submissions, and 130K matches. We saw tons of creativity, clever ideas, and real progress in learning. We’re now releasing it publicly to support RL education and experimentation. Try it out and train your own agent at 🔗
0:28

Last semester, I taught Reinforcement Learning class again at UCLA. Together with my amazing TAs Matthew and Caiyuan, we built a mini-project: MetaDrive Arena 🚗🤖 Students applied what they learned in class, trained RL agents, and competed on a live leaderboard. The results were incredible, with 94 agents, 2K submissions, and 130K matches. We saw tons of creativity, clever ideas, and real progress in learning. We’re now releasing it publicly to support RL education and experimentation. Try it out and train your own agent at 🔗

Bolei Zhou

25,253 Aufrufe • vor 3 Monaten

The network for machine intelligence Two years ago, we laid out our vision for a machine learning compute protocol. One that connects every device in the world into an open network for machine intelligence, with no gatekeepers or artificial boundaries. This week, we’ll be sharing some of our early progress, beginning with RL Swarm, a peer-to-peer system for collaborative reinforcement learning over the internet. Next month, we’ll open our Testnet, allowing anyone to contribute to the frontier of open machine intelligence. Introducing RL Swarm RL Swarm is a fully open source system for collaborative reinforcement learning over the internet. It is a live demo of our research findings, which show that models training with RL learn faster when they train as a collective swarm than they do on their own. Join our swarm now to see this in practice. You can participate with consumer hardware at home or a powerful GPU in the cloud. You can follow along with the swarm’s progress by following the links below.
0:28

The network for machine intelligence Two years ago, we laid out our vision for a machine learning compute protocol. One that connects every device in the world into an open network for machine intelligence, with no gatekeepers or artificial boundaries. This week, we’ll be sharing some of our early progress, beginning with RL Swarm, a peer-to-peer system for collaborative reinforcement learning over the internet. Next month, we’ll open our Testnet, allowing anyone to contribute to the frontier of open machine intelligence. Introducing RL Swarm RL Swarm is a fully open source system for collaborative reinforcement learning over the internet. It is a live demo of our research findings, which show that models training with RL learn faster when they train as a collective swarm than they do on their own. Join our swarm now to see this in practice. You can participate with consumer hardware at home or a powerful GPU in the cloud. You can follow along with the swarm’s progress by following the links below.

gensyn

228,703 Aufrufe • vor 1 Jahr

If a model is 50% reliable, it's 0% useful. Michael Giannangeli, Head of Agentic AI at Amazon Nova, breaks down one of the hardest problems in agentic AI: reliability. Models need to match or beat human performance, or they won't get adopted. To close the gap, teams are building an ecosystem of reinforcement learning "gyms" where AI agents can hone their skills. Think of it like a virtual training ground where agents practice tasks through trial and error, building reliability one rep at a time. 💪
1:16

If a model is 50% reliable, it's 0% useful. Michael Giannangeli, Head of Agentic AI at Amazon Nova, breaks down one of the hardest problems in agentic AI: reliability. Models need to match or beat human performance, or they won't get adopted. To close the gap, teams are building an ecosystem of reinforcement learning "gyms" where AI agents can hone their skills. Think of it like a virtual training ground where agents practice tasks through trial and error, building reliability one rep at a time. 💪

Amazon

35,008 Aufrufe • vor 2 Monaten

Jynxzi was excited after learning the number one rule on League of Legends as Jungler, which is never helping your team and only care about yourself 😭 “I’m a league player and I HATE my team… Jungle is the best thing in the game”
1:00

Jynxzi was excited after learning the number one rule on League of Legends as Jungler, which is never helping your team and only care about yourself 😭 “I’m a league player and I HATE my team… Jungle is the best thing in the game”

ryan 🤿

373,163 Aufrufe • vor 2 Monaten

Building a machine learning model isn’t just about finding the right algorithm—it’s about the right process. In Machine Learning in Production, Andrew Ng breaks down the iterative loop of model development: training, error analysis, refining hyperparameters, and improving data. Getting to a high test set accuracy is one thing, but aligning your model with real-world business metrics? That’s where the real challenge begins. Learn how to bridge the gap between models and impact:
1:19

Building a machine learning model isn’t just about finding the right algorithm—it’s about the right process. In Machine Learning in Production, Andrew Ng breaks down the iterative loop of model development: training, error analysis, refining hyperparameters, and improving data. Getting to a high test set accuracy is one thing, but aligning your model with real-world business metrics? That’s where the real challenge begins. Learn how to bridge the gap between models and impact:

DeepLearning.AI

45,248 Aufrufe • vor 1 Jahr

This is a neural network flying a drone at extremely high speed, beating human champions in FPV drone racing. - Reinforcement learning as a tool is so marvelously versatile. It's able to solve both fast, reactive tasks and slow, deliberate tasks (ChatGPT RLHF). - Trained in large-scale simulation, finetuned in real world - I believe this is the paradigm that will get us to generalist robot some day. Published on Nature's cover, "Champion-Level Drone Racing using Deep Reinforcement Learning." Authors: Elia Kaufmann, Leonard Bauersfeld, Antonio Loquercio, Matthias Müller, Vladlen Koltun & Davide Scaramuzza
1:18

This is a neural network flying a drone at extremely high speed, beating human champions in FPV drone racing. - Reinforcement learning as a tool is so marvelously versatile. It's able to solve both fast, reactive tasks and slow, deliberate tasks (ChatGPT RLHF). - Trained in large-scale simulation, finetuned in real world - I believe this is the paradigm that will get us to generalist robot some day. Published on Nature's cover, "Champion-Level Drone Racing using Deep Reinforcement Learning." Authors: Elia Kaufmann, Leonard Bauersfeld, Antonio Loquercio, Matthias Müller, Vladlen Koltun & Davide Scaramuzza

Jim Fan

598,669 Aufrufe • vor 2 Jahren