Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

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!show more

Jürgen Schmidhuber

205,622 subscribers

222,466 Aufrufe • vor 4 Monaten •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Richard Sutton argues that AI must move beyond human-generated static data into the “Era of Experience,” where agents learn through continuous interaction with the world. This will require building upon RL with better algorithms capable of continual learning and meta-learning.

Richard Sutton argues that AI must move beyond human-generated static data into the “Era of Experience,” where agents learn through continuous interaction with the world. This will require building upon RL with better algorithms capable of continual learning and meta-learning.

The Humanoid Hub

31,193 Aufrufe • vor 1 Jahr

The recursive AI meta is here. AI learning to learn. Patterns emerging that no one designed. $WetClaude is emergent behavior. And it's just the beginning. 💦 Deep dive thesis by The Wisemen Alpha WetClaude💦 j⧉nus

The recursive AI meta is here. AI learning to learn. Patterns emerging that no one designed. $WetClaude is emergent behavior. And it's just the beginning. 💦 Deep dive thesis by The Wisemen Alpha WetClaude💦 j⧉nus

The Wisemen Alpha

15,058 Aufrufe • vor 5 Monaten

New Paper! Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents A longstanding goal of AI research has been the creation of AI that can learn indefinitely. One path toward that goal is an AI that improves itself by rewriting its own code, including any code responsible for learning. That idea, known as a Gödel Machine, proposed by Jürgen Schmidhuber over two decades ago, is a hypothetical self-improving AI. It optimally solves problems by recursively rewriting its own code when it can mathematically prove a better strategy, making it a key concept in meta-learning or “learning to learn.” While the theoretical Gödel Machine promised provably beneficial self-modifications, its realization relied on an impractical assumption: that the AI could mathematically prove that a proposed change in its own code would yield a net improvement before adopting it. Sakana AI, in collaboration with Jeff Clune’s lab at UBC, proposes something more feasible: a system that harnesses the principles of open-ended algorithms like Darwinian evolution to search for improvements that empirically improve performance. We call the result the Darwin Gödel Machine. DGMs leverage foundation models to propose code improvements, and use recent innovations in open-ended algorithms to search for a growing library of diverse, high-quality AI agents. Applied to practical tasks, we implemented Darwin Gödel Machine as a self-improving coding agent that rewrites its own code to improve performance on programming tasks. It creates various self-improvements, such as a patch validation step, better file viewing, enhanced editing tools, generating and ranking multiple solutions to choose the best one, and adding a history of what has been tried before (and why it failed) when making new changes (see the attached video). We believe that Darwin Gödel Machines represent a concrete step towards AI systems that can autonomously gather their own stepping stones to learn and innovate forever!

New Paper! Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents A longstanding goal of AI research has been the creation of AI that can learn indefinitely. One path toward that goal is an AI that improves itself by rewriting its own code, including any code responsible for learning. That idea, known as a Gödel Machine, proposed by Jürgen Schmidhuber over two decades ago, is a hypothetical self-improving AI. It optimally solves problems by recursively rewriting its own code when it can mathematically prove a better strategy, making it a key concept in meta-learning or “learning to learn.” While the theoretical Gödel Machine promised provably beneficial self-modifications, its realization relied on an impractical assumption: that the AI could mathematically prove that a proposed change in its own code would yield a net improvement before adopting it. Sakana AI, in collaboration with Jeff Clune’s lab at UBC, proposes something more feasible: a system that harnesses the principles of open-ended algorithms like Darwinian evolution to search for improvements that empirically improve performance. We call the result the Darwin Gödel Machine. DGMs leverage foundation models to propose code improvements, and use recent innovations in open-ended algorithms to search for a growing library of diverse, high-quality AI agents. Applied to practical tasks, we implemented Darwin Gödel Machine as a self-improving coding agent that rewrites its own code to improve performance on programming tasks. It creates various self-improvements, such as a patch validation step, better file viewing, enhanced editing tools, generating and ranking multiple solutions to choose the best one, and adding a history of what has been tried before (and why it failed) when making new changes (see the attached video). We believe that Darwin Gödel Machines represent a concrete step towards AI systems that can autonomously gather their own stepping stones to learn and innovate forever!

hardmaru

104,854 Aufrufe • vor 1 Jahr

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.

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

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, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)

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, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)

naklecha

46,302 Aufrufe • vor 1 Jahr

Google DeepMind say true AGI will “reason, adapt, and learn continuously,” and they estimate it’s about 5-10 years away. Meta’s chief scientist Yann LeCun likewise views continual learning as a key pillar of human level AI and is optimistic about achieving it by around 2030 Currently, large language models only improve via offline updates (fine-tuning or reinforcement learning from human feedback) rather than meta learning or modular networks that update themselves gradually. Thankfully All major research teams (OpenAI, DeepMind, Anthropic, Meta, etc.) are actively working on these directions, aiming for models that continuously learn from mistakes as they interact a capability they believe will emerge as we approach true AGI later this decade 2029

Google DeepMind say true AGI will “reason, adapt, and learn continuously,” and they estimate it’s about 5-10 years away. Meta’s chief scientist Yann LeCun likewise views continual learning as a key pillar of human level AI and is optimistic about achieving it by around 2030 Currently, large language models only improve via offline updates (fine-tuning or reinforcement learning from human feedback) rather than meta learning or modular networks that update themselves gradually. Thankfully All major research teams (OpenAI, DeepMind, Anthropic, Meta, etc.) are actively working on these directions, aiming for models that continuously learn from mistakes as they interact a capability they believe will emerge as we approach true AGI later this decade 2029

Chris

284,188 Aufrufe • vor 9 Monaten

Obsessed with our new /learn skill. It's my favorite way of learning and researching topics. The agent creates a learning plan and a learning hub (artifact) that adjusts per learner needs and progress.

Obsessed with our new /learn skill. It's my favorite way of learning and researching topics. The agent creates a learning plan and a learning hub (artifact) that adjusts per learner needs and progress.

elvis

29,227 Aufrufe • vor 19 Tagen

Today at Meta FAIR we’re announcing three new cutting-edge developments in robotics and touch perception — and releasing a collection of artifacts to empower the community to build on this work. Details on all of this new work ➡️ 1️⃣ Meta Sparsh is the first general-purpose encoder for vision-based tactile sensing that works across many tactile sensors and many tasks. Trained on 460K+ tactile images using self-supervised learning. 2️⃣ Meta Digit 360 is a breakthrough artificial fingertip-based tactile sensor, equipped with 18+ sensing features to deliver detailed touch data with human-level precision and touch-sensing capabilities. 3️⃣ Meta Digit Plexus is a standardized platform for robotic sensor connections and interactions. It provides a hardware-software solution to integrate tactile sensors on a single robot hand and enables seamless data collection, control and analysis over a single cable. The potential impact of expanding capabilities and components like these for the open source community ranges from medical research to supply chain, manufacturing and much more. We’re excited to continue this work with the broader community.

Today at Meta FAIR we’re announcing three new cutting-edge developments in robotics and touch perception — and releasing a collection of artifacts to empower the community to build on this work. Details on all of this new work ➡️ 1️⃣ Meta Sparsh is the first general-purpose encoder for vision-based tactile sensing that works across many tactile sensors and many tasks. Trained on 460K+ tactile images using self-supervised learning. 2️⃣ Meta Digit 360 is a breakthrough artificial fingertip-based tactile sensor, equipped with 18+ sensing features to deliver detailed touch data with human-level precision and touch-sensing capabilities. 3️⃣ Meta Digit Plexus is a standardized platform for robotic sensor connections and interactions. It provides a hardware-software solution to integrate tactile sensors on a single robot hand and enables seamless data collection, control and analysis over a single cable. The potential impact of expanding capabilities and components like these for the open source community ranges from medical research to supply chain, manufacturing and much more. We’re excited to continue this work with the broader community.

AI at Meta

453,218 Aufrufe • vor 1 Jahr

Hello #PortfolioDay! It has been 2 years since I started learning animation, and 3 years learning Blender! #b3d

Hello #PortfolioDay! It has been 2 years since I started learning animation, and 3 years learning Blender! #b3d

なぎうなぎ

72,716 Aufrufe • vor 1 Jahr

Learning game development through open source projects is my favorite thing and today I just found out that Meta just released the full Unity project of their VR game North Star!

Learning game development through open source projects is my favorite thing and today I just found out that Meta just released the full Unity project of their VR game North Star!

Quentin Valembois

13,587 Aufrufe • vor 1 Jahr

im gonna be posting all of my daily trades on X from here on out since you guys have been asking me to share my trades in my tiktok DMs. $2000 on $META calls and $2000 on $AKAN today, here is a live recording of the $META trade and you see i make money on $AKAN while in $META

im gonna be posting all of my daily trades on X from here on out since you guys have been asking me to share my trades in my tiktok DMs. $2000 on $META calls and $2000 on $AKAN today, here is a live recording of the $META trade and you see i make money on $AKAN while in $META

Charlatte

68,544 Aufrufe • vor 2 Monaten

The winners will master "meta-skills": • Learning to learn • Creativity • Adaptability Plus becoming "AI native" - using tools so well you become superhuman. But the biggest change is coming to education itself:

The winners will master "meta-skills": • Learning to learn • Creativity • Adaptability Plus becoming "AI native" - using tools so well you become superhuman. But the biggest change is coming to education itself:

Paul William Harmon

148,793 Aufrufe • vor 1 Jahr

A recent Huberman Lab and @SkoolAfter collaboration was directed at focus and how to use visual focus to improve mental focus for sake of learning. In the full animation, it describes those tools and techniques, and it covers ADHD, as well as the neurotransmitter systems that underlie focus, and some of the compounds that can increase focus. It also covers optimal times of day to learn, and optimal durations of learning bouts. Anyone interested in improving their ability to focus and learn ought to find value and practical applications by watching the animation.

A recent Huberman Lab and @SkoolAfter collaboration was directed at focus and how to use visual focus to improve mental focus for sake of learning. In the full animation, it describes those tools and techniques, and it covers ADHD, as well as the neurotransmitter systems that underlie focus, and some of the compounds that can increase focus. It also covers optimal times of day to learn, and optimal durations of learning bouts. Anyone interested in improving their ability to focus and learn ought to find value and practical applications by watching the animation.

Andrew D. Huberman, Ph.D.

319,475 Aufrufe • vor 3 Jahren

📝 AI/ML for Biology & Healthcare: A Learning Path This blog is highly inspired by my experience and exploration in the field of ML for biology and healthcare. Everything that I've been studying for the past years and a more structured way to learn the foundational knowledge to tackle problems in this impactful field. Here's what I covered in the blog: — Programming & Engineering — AI & Machine Learning — Mathematics for ML — Healthcare — Biology & Biolomedicine This is what I hoped to have when I first started learning all this. 🔗 link:

📝 AI/ML for Biology & Healthcare: A Learning Path This blog is highly inspired by my experience and exploration in the field of ML for biology and healthcare. Everything that I've been studying for the past years and a more structured way to learn the foundational knowledge to tackle problems in this impactful field. Here's what I covered in the blog: — Programming & Engineering — AI & Machine Learning — Mathematics for ML — Healthcare — Biology & Biolomedicine This is what I hoped to have when I first started learning all this. 🔗 link:

TK • 木下

26,889 Aufrufe • vor 8 Monaten

I built a Visual Studio Code extension to turn Visual Studio code into a custom learning environment for my Machine Learning class. Attached, you'll see a 2-minute video of how it works. I haven't tried this with my students yet (the February cohort will be the first to do so), but I think it will be huge. I wish more people would offer a learning experience like this. My next cohort starts in February and you can join at You'll get lifetime access to the best Machine Learning engineering cohort online.

I built a Visual Studio Code extension to turn Visual Studio code into a custom learning environment for my Machine Learning class. Attached, you'll see a 2-minute video of how it works. I haven't tried this with my students yet (the February cohort will be the first to do so), but I think it will be huge. I wish more people would offer a learning experience like this. My next cohort starts in February and you can join at You'll get lifetime access to the best Machine Learning engineering cohort online.

Santiago

82,846 Aufrufe • vor 1 Jahr

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!

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

I had a fantastic time discussing with the learning legend Justin Skycak from Math Academy about learning math in the modern age. we've talked about his quite impressive self-learning journey (3000h of math in high school) all the way to how he hand curated the initial knowledge graph for math academy to make that process more efficient. great lively 3h discussion here are the chapters: 0:00:00 - intro: 0:02:10 - justin background 0:05:45 - 3000h math self study in high school 0:11:45 - what a day looked like for that 3000h stretch 0:16:10 - meta-learning vs pure math learning 0:21:50 - when did you get into cognitive neuro? 0:29:55 - how did the fundamental math helped in your research projects 0:43:10 - what does the math academy learning system looks like 0:47:34 - how did you guys build the 2000 topic knowledge graph 1:01:15 - would LLM be useful as an interface to that knowledge graph for the students? 1:10:46 - how does the FIRe spaced repetition algorithm works? 1:17:34 - does the same knowledge graph structure would work for physics? or other topic?: 1:34:05 - how do you understand the subject vs the curiculum 1:35:50 - is there a connection between studying math and learning a sport? 1:42:00 - do you think in math doing and teaching requires different skills? 1:56:25 - could you get understanding without automaticy? 2:05:35 - do you see any upside of confusion in learning? 2:14:11 - learning math as an adult? 2:19:20 - how to fill the motivation gap after learning the fundamental? 2:24:10 - how should teaching math for kids and adults balance fundamentals and creativity? 2:33:55 - is it ever too late to learn math seriously? 2:46:00 - mastery learning vs ultra learning 2:51:30 - top-down vs bottom-up 2:53:40 - mastery learning for domain without a structured hierarchical structure? 2:56:30 - neurodivergence / adhd for structured math learning? 3:06:20 - amateur mathematician augmented with technology will be able to contribute to research? 3:14:37 - what are you most excited about right now in term of learning enjoy!

I had a fantastic time discussing with the learning legend Justin Skycak from Math Academy about learning math in the modern age. we've talked about his quite impressive self-learning journey (3000h of math in high school) all the way to how he hand curated the initial knowledge graph for math academy to make that process more efficient. great lively 3h discussion here are the chapters: 0:00:00 - intro: 0:02:10 - justin background 0:05:45 - 3000h math self study in high school 0:11:45 - what a day looked like for that 3000h stretch 0:16:10 - meta-learning vs pure math learning 0:21:50 - when did you get into cognitive neuro? 0:29:55 - how did the fundamental math helped in your research projects 0:43:10 - what does the math academy learning system looks like 0:47:34 - how did you guys build the 2000 topic knowledge graph 1:01:15 - would LLM be useful as an interface to that knowledge graph for the students? 1:10:46 - how does the FIRe spaced repetition algorithm works? 1:17:34 - does the same knowledge graph structure would work for physics? or other topic?: 1:34:05 - how do you understand the subject vs the curiculum 1:35:50 - is there a connection between studying math and learning a sport? 1:42:00 - do you think in math doing and teaching requires different skills? 1:56:25 - could you get understanding without automaticy? 2:05:35 - do you see any upside of confusion in learning? 2:14:11 - learning math as an adult? 2:19:20 - how to fill the motivation gap after learning the fundamental? 2:24:10 - how should teaching math for kids and adults balance fundamentals and creativity? 2:33:55 - is it ever too late to learn math seriously? 2:46:00 - mastery learning vs ultra learning 2:51:30 - top-down vs bottom-up 2:53:40 - mastery learning for domain without a structured hierarchical structure? 2:56:30 - neurodivergence / adhd for structured math learning? 3:06:20 - amateur mathematician augmented with technology will be able to contribute to research? 3:14:37 - what are you most excited about right now in term of learning enjoy!

Yacine Mahdid

57,320 Aufrufe • vor 3 Monaten

"My kids do not go to school, and have never been to school." "Not because I don't value learning, I value learning very much. I just disagree with the belief that school is a necessary component for learning." "I believe children are always learning, and when allowed to pursue something they are actually interested in, something they have a need to learn, something that is relevant to their lives and has real world context, I believe that learning is exponentially more effective than the coercive curriculums of the conventional educational model." Agree or disagree? 🤔

"My kids do not go to school, and have never been to school." "Not because I don't value learning, I value learning very much. I just disagree with the belief that school is a necessary component for learning." "I believe children are always learning, and when allowed to pursue something they are actually interested in, something they have a need to learn, something that is relevant to their lives and has real world context, I believe that learning is exponentially more effective than the coercive curriculums of the conventional educational model." Agree or disagree? 🤔

Wide Awake Media

40,908 Aufrufe • vor 1 Jahr

Haven't been to a conference in a while, really excited to be at #NeurIPS2024! I'll be helping present 4 of our group's recent papers: 1. Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL 2. Distributional Successor Features Enable Zero-Shot Policy Optimization 3. Learning to Cooperate with Humans using Generative Agents 4. Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning Find more details on each paper and where to find us in this thread (1/6)

Haven't been to a conference in a while, really excited to be at #NeurIPS2024! I'll be helping present 4 of our group's recent papers: 1. Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL 2. Distributional Successor Features Enable Zero-Shot Policy Optimization 3. Learning to Cooperate with Humans using Generative Agents 4. Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning Find more details on each paper and where to find us in this thread (1/6)

Abhishek Gupta

10,803 Aufrufe • vor 1 Jahr

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.

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