Google DeepMind is absolutely on fire 🔥 they have... just launched Gemini Robotics-ER 1.5 their first broadly available robotics AI model designed to act as the "high-level reasoning brain" for robots. This is Google's first Gemini Robotics model made available to all developers. - Available in preview through Google AI Studio and Gemini API. - First thinking model for robots interacting with the physical world. Handles complex commands and orchestrates sophisticated robotic behaviors. - Key capabilities: Advanced spatial reasoning, multi-step task planning, Google Search integration, precise 2D pointing, object reasoning, and video analysis. - Flexible thinking budget lets developers tune speed vs accuracy. Can think longer for complex tasks or respond quickly for reactive operations. - Enhanced safety filters refuse dangerous tasks and recognize physical limits.show more

Woow Google has just rolled out the AI model... Flash Thinking 2.0 This is the first reasoning model capable of accessing YouTube and it changes everything: - Search for a video on your topic - Ask Gemini to think about the video - You'll have a tailor-made result in 10 sec. And it's even connected to Google Search and Maps!show more

1/ Gemini 2.5 is here, and it’s our most... intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.show more

The Gemini 2.0 era is here. And we’re excited... for you to start building with it. A quick rewind of what we just released ⏪ Gemini 2.0 Flash ⚡ comes with low latency and better performance. 🔵 You can now access an experimental version in G3mini on the web, while Gemini Advanced users can try Deep Research, a new AI research assistant. 🔵 Developers can begin building through the Gemini API in Google AI Studio and Vertex AI 2.0 is also enabling new research prototypes of AI agents, including: 🔵 Project Astra, which explores future capabilities of a universal AI assistant 🔵 Project Mariner, which shows what’s possible for human-agent interaction, starting with your browser 🔵 Jules, an experimental AI-powered coding agent Finally, we’re exploring how 2.0 can be used in agents across domains — from navigating the virtual world of video games to applying its spatial reasoning capabilities to robotics. 🤖show more

Gemma 4 is here! Our most intelligent open models... to date, are built on the same world-class research and tech as Gemini 3, and are sized to run and fine-tune efficiently on local hardware. Check out what Google Gemma 4 brings to devs: 💎 Advanced Reasoning: Deep logic tasks, complex multi-step planning, and beyond 💎 Longer context: Seamlessly analyze entire codebases with context windows of 128K tokens for our edge models and 256K tokens for our largest models 💎 Vision and audio: Rich, multimodal interactions out of the box 💎 140+ languages: Trained on 140+ languages 💎 Apache 2.0 license: industry-standard open-source licenseshow more

SoftBank is reportedly in early talks to back a... massive $800M funding round for Munich-based Agile Robots, with a contribution of over $ 300M. The move signals a major escalation in Masayoshi Son's "brains and bodies" strategy to dominate physical AI infrastructure. Why this matters for the robotics industry: 🤖 The Flywheel: Agile Robots isn't just hardware. Founded by German Aerospace Center (DLR) alumni, they vertically integrate AI software with humanoids, warehouse automation, and robotic arms. 🧠 Frontier Ecosystems: Agile ONE was recently named a founding member of NVIDIA’s Cosmos Coalition and is deep in a research partnership with Google DeepMind to bring Gemini to the factory floor. 💰 The Capital Race: Global investment in robotics more than tripled in 2025. SoftBank is pairing this hardware play with its recent $1.4B investment in Skild AI and its $5.4B acquisition of ABB Robotics. While both companies have declined to comment on the early-stage talks, the deal highlights a furious shift toward deploying foundational AI in physical manufacturing and logistics.show more

Moonshot AI is casually giving developers free daily access... to Kimi K3 😳 no subscription no upfront payment just sign in and start using one of the largest open AI models available what you get for $0: - Kimi K3 with 2.8T parameters - 1M token context window - strong coding and reasoning performance - native vision capabilities - free daily credits that refresh automatically why this is worth checking: > access a frontier model without paying API fees > long context for large codebases and documents > works on web, desktop, mobile, and CLI getting started takes less than 2 minutes: 1. go to 2. create a free account 3. Kimi K3 is available as the default model 4. start chatting or coding with your daily free credits bonus: Moonshot Together lets you invite friends for a chance to earn 3, 7, 15, 30, or even 365 days of Kimi Membership through its rewards program benchmark highlights: > 2.8T parameter MoE model > 1M context window > strong performance across coding, browsing, and reasoning benchmarks important: free credits reset daily, rate limits apply on the free tier, and the open-weight release is expected on July 27 A simple way to try one of the latest frontier AI models without paying for API accessshow more

I spent a month in Shenzhen visiting factories and... robotics companies, and the contrast with the U.S. was striking. While Figure and Boston Dynamics hide their humanoids behind closed doors, Chinese companies have massive showrooms open to the public. But what really stood out wasn't just the transparency, it was how good they are at selling. Take UBTech: they've already sold 1,200 humanoid units at $200k each to factories. And here's the kicker, these robots aren't even that useful yet. They can only pick up and drop boxes at 1/10th the speed of a human, and factories still need to hire system integrators to train them for specific tasks. My theory is that these factories are terrified of getting left behind in the robotics/AI wave. They're investing in new tech not because it's ready, but because they can't afford to wait. The second surprise was the breadth of their robotics portfolio. These companies aren't just building humanoids, they're deploying service robots everywhere: restaurants, hotels, apartments. Consumer robots are cleaning houses, pools, pet waste, dishes. They're covering the entire spectrum. But the education piece shocked me most. I picked up what I thought was a high school or college robotics textbook, it was for primary school. The government mandated AI and robotics education starting in elementary school. Almost every single school in China now has AI and robotics curriculum, complete with education robots so kids can learn by building. They're creating a generation that grows up fluent in robotics and AI. China owns the supply chain and the hardware stack. But here's what I think people are missing: the race isn't just about who can build robots faster or cheaper. The U.S. advantage has always been in the layer between hardware and human, the interaction design, the software intelligence, the intuitive interfaces that make complex technology feel natural. China is building the physical infrastructure, but they're also learning fast. Every deployed service robot, every classroom full of kids building with education kits, every factory running humanoids, that's all data collection at scale. The window for the U.S. to establish its wedge is narrowing. It's not enough to be better at AI or software anymore. We need to be building the integration layer, the intelligence that makes physical AI actually useful, not just impressive in a showroom. Because right now, China isn't just manufacturing robots. They're manufacturing a robotics-native culture, and that might be the most defensible moat of all.show more

OpenAI's AgentKit will be so insane, build every step... of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAI’s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAI’s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agent—from visual design to deployment and performance tuning—inside a single unified system.show more

Your AI Toolkit Just Got Supercharged 5 elite AI... models. 1 unified platform. 90 seconds of pure workflow magic. Here's the reality: Building with AI used to mean chaos—juggling tabs, managing API keys, context-switching hell. But what if you didn't have to choose? What if you could access the best of every model without leaving your workflow? Meet the New Standard: Replit's AI Model Ecosystem Claude for your complex thinking. GPT-4 for your creative fire. Mistral when you need lightning-speed execution. Llama for privacy-first local analysis. Open source freedom for the innovators. 300+ models. One dashboard. Zero friction. Switch between them in seconds, not minutes. No sign-ups. No API gymnastics. Just pick, prompt, and ship. Why This Matters You're not just saving time—you're reclaiming your focus. Every tab you don't open is mental energy preserved. Every API key you don't manage is a distraction eliminated. This is what AI integration should feel like: invisible. Effortless. Natural. The builders who master this first won't just be faster. They'll be unstoppable. Your move. Replit ⠕ is waiting. ✨show more

🚀 Early Access to Sahara AI Studio is NOW... OPEN! The next phase of our testnet is here with exclusive early access to our all-in-one platform designed to transform the AI development lifecycle into a streamlined, integrated experience. Here’s everything you need to know 👇 AI development is fragmented. Devs juggle multiple tools, leading to inefficiencies & high costs. Sahara AI Studio integrates the entire AI lifecycle—from datasets & model training to secure storage & scalable compute—into one seamless experience: 📊 Data Hub: Discover, Manage, and Leverage AI-Ready Datasets Access high-quality, domain-specific, open-source and proprietary datasets through an integrated marketplace. Developers can download, import, or label datasets, making it easier to train and fine-tune models or deploy RAG pipelines. Secure uploads and seamless workflow integration enhance the experience. 🤖 Model Hub: Discover, Customize and Scale AI Workflows with Ease Discover ready-to-use open-source and proprietary models, RAG pipelines, and customizable workflows. Developers can deploy models quickly while maintaining privacy and security through Sahara Vaults. 🖥️ Compute Hub: Flexible, Scalable Compute Resources for AI Innovation Access scalable and secure computing resources tailored to diverse AI workloads. Trusted Execution Environment (TEE) capabilities ensure data privacy, while integration with top compute providers offer flexibility for developers. 🔐 Vaults: Secure Storage for AI Assets Securely store, organize, and manage datasets, models, and other assets in an encrypted central repository. Vaults offer scalability, reproducibility, and user control over AI resources. This is more than just beta testing a platform—it's your chance to help shape the future of decentralized AI development. 📅 How to Apply We're onboarding select developers in a phased approach. Early Access spots are limited, so apply now:show more

HERMES AGENT NOW RUNS CLAUDE OPUS 5. NEAR FABLE... 5 INTELLIGENCE. HALF THE PRICE. SELF-VERIFIES ITS OWN WORK. AVAILABLE TODAY VIA NOUS PORTAL (20% OFF ALL MODELS). Anthropic shipped Opus 5 on July 24, 2026. same $5/$25 per million tokens as Opus 4.8. but the benchmarks tell a different story. WHAT CHANGED FROM OPUS 4.8: FrontierBench v0.1: Opus 5: 43.3%. Opus 4.8: 18.7%. 2.3x jump on the same test. ARC-AGI-3: Opus 5: 30.2%. 3x better than the next closest model. beat Fable 5 on 8 out of 13 benchmarks. at half the cost ($5/$25 vs $10/$50). same price as Opus 4.8. twice the intelligence. no reason to stay on 4.8. THE SPECS: model ID: claude-opus-5 context: 1M tokens (default and maximum) max output: 128K tokens thinking: on by default effort toggle: low / medium / high per request fast mode: $10/$50, 2.5x faster knowledge cutoff: May 2026 minimum cacheable prompt: 512 tokens (was 1,024) SELF-VERIFICATION (the biggest change): Opus 5 checks its own work automatically. Anthropic says: delete your verification prompts. "include a final verification step" now causes OVER-verification because the model already does it. for Hermes /goal tasks this is a direct upgrade. the judge checks evidence. the model also checks evidence. double layer of verification without extra tokens. EFFORT TOGGLE: low: fast, cheap, routine work. medium: balanced, daily tasks. high: full reasoning, complex problems. set per request. not a global switch. matches Hermes /reasoning command: /reasoning low (routine) /reasoning high (complex) Opus 5 effort toggle + Hermes reasoning control = precise cost management per turn. WHERE OPUS 5 FITS IN HERMES: DAILY DRIVER (replaces Opus 4.8): same price. 2.3x better benchmarks. set as your main model: Desktop app / Dashboard: Models → claude-opus-5 CHIEF OF STAFF: synthesis across multiple agents. reads Kanban, prioritizes, routes tasks. self-verification catches routing errors before they cascade. COMPLEX CODING: SOTA on agentic coding benchmarks. FrontierBench 43.3% = best public model for coding. set as coder profile model. /GOAL TASKS: self-verification + completion contracts = the model proves its work AND double-checks the proof. long-horizon goals finish correctly more often. MoA AGGREGATOR: strongest synthesis model at $5/$25. pair with GPT-5.6 and Grok 4.5 as references. Opus 5 aggregates. best quality at mid-range price. presets: max-quality: reference_models: - provider: openai-codex model: gpt-5.6-sol - provider: xai model: grok-4.5 aggregator: provider: anthropic model: claude-opus-5 COMPUTER USE: near-Fable 5 quality for browser automation. at half the token cost per session. computer_use tasks burn lots of vision tokens. Opus 5 halves that bill vs Fable 5. WHAT TO KEEP OPUS 5 AWAY FROM: cron monitoring: too expensive. use DeepSeek or no_agent mode. sub-agent grunt work: use GPT-5.6 Luna ($1/$6) or DeepSeek. auxiliary tasks: use Gemini Flash. routine web extraction: use a cheap model. Opus 5 is for the turns where quality compounds. planning, synthesis, verification, complex reasoning. budget models handle everything else. NOUS PORTAL: 20% OFF ALL MODELS Nous Portal currently runs a 20% discount on all models including Opus 5. $5/$25 official → $4/$20 through Nous Portal. the cheapest way to run Opus 5 right now. hermes setup --portal select claude-opus-5 as your model. discount applies automatically. Opus 5 replaces Opus 4.8 everywhere. same price. better at everything. no tradeoff. straight upgrade. hermes update /model claude-opus-5show more

Boom! Grok Tasks Make It One Of The Most... POWERFUL Real-Time AI Systems In The World. — My How to Use Grok Tasks With Hidden Tools For Powerful Daily Output. Grok Tasks are customizable AI workflows that integrate a variety of tools to streamline daily activities, from research and analysis to creative planning and problem-solving. I have been using them for quite sometime and because of the vital heartbeat of news and first person data on X, it is the most powerful AI platform available. By combining Tasks with tools like web searches, X platform interactions, code execution, and media viewers, you can build efficient, automated processes. These tasks work by prompting Grok with a clear description of what you want to achieve, and Grok will intelligently call the necessary tools in sequence or parallel to deliver results. Here's a step-by-step guide to creating and using Grok Tasks: Step 1: Define Your Task Start by clearly outlining the daily activity or goal. Consider what inputs you have (e.g., a URL, a query, or an attachment) and what output you need (e.g., a summary, calculation, or visual analysis). Break it down into subtasks to identify tool needs. For example, if your task involves researching current events, note that you'll need search and browsing capabilities. Step 2: Review Available Tools Familiarize yourself with the tools Grok can access. Here's a quick overview: - Code Execution: Run Python code for calculations, data processing, or simulations using libraries like numpy, pandas, or sympy. - Browse Page: Fetch and summarize content from any website URL with custom instructions. - Web Search: Perform general internet searches, returning results with optional operators like site:. - Web Search With Snippets: Get quick, detailed excerpts from search results for fact-checking. - X Keyword Search: Advanced search for X posts using operators like from:, since:, or filter:. - X Semantic Search: Find semantically related X posts based on a query, with filters for dates or users. - X User Search: Locate X users by name or handle. - X Thread Fetch: Retrieve a full X post thread, including context like replies and parents. - View Image: Analyze an image from a URL or conversation ID. - View X Video: Extract frames and subtitles from an X-hosted video. - Search PDF Attachment: Query a PDF file for relevant pages using keyword or regex modes. - Browse PDF Attachment: View specific pages of a PDF with text and screenshots. Select tools that align with your task. Aim for a mix to handle data gathering, processing, and visualization. Step 3: Craft Your Prompt Write a detailed prompt to Grok describing the task. Include: - The overall goal. - Specific steps or subtasks. - References to tools if you want to guide the process (e.g., "Use web_search to find sources, then code_execution to analyze data"). - Any constraints, like dates or limits. Example prompt: "Create a Grok Task for my morning routine: Search recent X posts about tech news using x_keyword_search, fetch a key thread with x_thread_fetch, and summarize with browse_page on linked articles." Step 4: Submit and Interact Send your prompt to Grok. It will process the task by calling tools as needed, often in parallel for efficiency. Review the output and refine with follow-up prompts if required (e.g., "Expand on that using view_image for visuals"). Iterate to fine-tune the workflow for reuse. Step 5: Save and Reuse Once refined, note the prompt as a template for future use. You can adapt it for similar tasks, making Grok Tasks a habitual part of your day. Finding Grok Tasks To discover existing Grok Tasks or inspiration for new ones, use X searches with tools like x_keyword_search or x_semantic_search (e.g., query: "Grok Tasks examples" with mode: Latest). Browse community-shared threads via x_thread_fetch, or web_search for tutorials on xAI features. Prompt Grok directly: "Show me popular Grok Tasks for productivity." 1 of 3show more

A Letter to Our Community: The Road Ahead for... Robotics To our Community and Partners, As we step into 2026, our mission at Axis is clearer than ever: Constructing the definitive End-to-End Scaling Layer for Robotics. Our goal is to accelerate the transfer of diverse human intelligence into Robotics General Intelligence (RGI). By owning the critical path of intelligence creation, we are turning the physical limitations of robotics into a scalable, software-driven future. Here is our strategic outlook and roadmap for the year ahead. The Core Thesis: Simulation is the Only Way Out The path to RGI is currently blocked by Data Scarcity, Generalization Fragility, and Hardware Fragmentation. At Axis, we believe Simulation is the only way out. Our Simulation Data Platform and Data Augmentation Engine transform raw data into "Synthetic Gold". Backed by academic milestones like Roboverse, Skill Blending, and GraspVLA, we have proven that pure simulation can achieve the generalization required for the real world. We don’t just collect data; we architect it. The Engine: Why Crypto? We believe RGI should come from all, not a few. Crypto is not just a feature; it is the primitive that powers our entire ecosystem flywheel: - Incentive Mechanism: Democratizing contribution and rewarding the trainers and developers. - Assetization: Turning proprietary data and refined models into liquid, ownable assets. - Verifiable Workflow: We are opening the "Black Box" of AI. By bringing total transparency to the Task Generation → Data Collection → Model Training pipeline, we ensure every byte of intelligence is verifiable, traceable, and secure. 2026 Strategic Deliverables This year, we are committed to delivering three foundational pillars: - The World's Largest Training Dataset for Robots: A robot training set—diverse, high-quality interaction data at an unprecedented scale. - A Robotics Foundation Model: A universal robotic brain trained on our pure simulation and synthetic data, capable of robust cross-embodiment transfer and open-world adaptability. - Evolvable Robot Hardware: Robots deployed with Axis models that autonomously evolve through continuous interaction, turning every deployment into a self-improving node within our RGI network. The Ultimate Vision We are building more than models; we are architecting the Distributed Machine Economy. A future where every dataset, model, and robotic embodiment is a verifiable asset in a global, autonomous network. Thank you for building the future of intelligence with us✌️📷show more

Robora Sim: A PyBullet-Powered Environment for Learning Robotic Physical... Intelligence We are currently building our Robora simulation environment setup for our sim based learning, leveraging PyBullet, an industry-standard physics engine widely used in AI-driven robotics research and development. The environment is optimized with GPU-accelerated learning algorithms, enabling high-speed imitation learning and reinforcement learning within a safe and controlled virtual setup before shipping out to real world. This simulation platform allows our models to learn, adapt, and generalize across different robot morphologies, terrain types and task objectives - all before deployment to the real world. At it's core, the system combines a VLA-powered high-level planner with low-level motion control algorithms, working cohesively to produce emergent, physically intelligent behaviors. This synergy between simulation, learning, and real-world transfer marks a major step forward in our pursuit of adaptive and intelligent robotic systems. Through advanced domain randomization and synthetic data generation, the Robora Simulation Environment ensures that policies trained in simulation transfer effectively to real-world robots, minimizing the sim-to-real gap. Moreover, users will be able to test and integrate their own hardware kits within selected simulation environments in the Robora Dapp, ensuring seamless compatibility and safer real-world implementation.show more

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft paper... page: Constructing AI models that respond to text instructions is challenging, especially for sequential decision-making tasks. This work introduces an instruction-tuned Video Pretraining (VPT) model for Minecraft called STEVE-1, demonstrating that the unCLIP approach, utilized in DALL-E 2, is also effective for creating instruction-following sequential decision-making agents. STEVE-1 is trained in two steps: adapting the pretrained VPT model to follow commands in MineCLIP's latent space, then training a prior to predict latent codes from text. This allows us to finetune VPT through self-supervised behavioral cloning and hindsight relabeling, bypassing the need for costly human text annotations. By leveraging pretrained models like VPT and MineCLIP and employing best practices from text-conditioned image generation, STEVE-1 costs just $60 to train and can follow a wide range of short-horizon open-ended text and visual instructions in Minecraft. STEVE-1 sets a new bar for open-ended instruction following in Minecraft with low-level controls (mouse and keyboard) and raw pixel inputs, far outperforming previous baselines. We provide experimental evidence highlighting key factors for downstream performance, including pretraining, classifier-free guidance, and data scaling. All resources, including our model weights, training scripts, and evaluation tools are made available for further research.show more

🚨China vs USA robots Chinese robot: $24,000 American robot:... $39,100 Pricing policy isn't everything. If we look at real capabilities, the balance of power looks completely different 🇨🇳 The robot demonstrates incredible agility, confidently performs a backflip, moves dynamically, and dances Maximum flexibility, high tech at an affordable price, and readiness for real-world tasks 🇺🇸 The robot, with a higher price tag, currently looks more modest, struggling even with basic rectilinear walking An obvious overpayment for brand and marketing, while Chinese engineers are outpacing competitors in software and hardware The main paradox of the current moment is that Chinese companies focus on rapidly cheapening hardware and mass production, turning robotics into an accessible mass-market consumer product. Meanwhile, the US traditionally tries to enter the market through fundamental neural networks and a universal AI brain However, in the coming years, we will see the inevitable convergence of these approaches: the winner in this race will not be the one who simply teaches a robot to do a backflip or walk straight, but the one who first combines Chinese cheap and adaptive mechatronics with advanced American language and multimodal models And what do you think, who will ultimately set the global standard in robotics East or West?show more

Model-Free Reinforcement Learning (MFRL) has been alluring, especially with... supercharged compute with physics on GPU. However, the methods use 0-th order gradients, and are often not the best optimizers. Can we do better than PPO in continuous control for robotics? Turns out yes! 🥳 tl;dr: Faster, better RL than PPO in continuous control 💪 The answer lies in using more information from the simulation. We are juicing the simulation on GPU as it is, why not use it for gradients as well? This has been a driving question in a series of our works. We first studied this problem in ICLR 2022 paper on Short Horizon Actor Critic Naive gradient based methods are stuck in local minima and have exploding/vanishing gradients. SHAC solved this problem truncated rollouts and model based value estimation, where the model is Differentiable Sim. This boosted sample efficiency and wall-clock time immensely especially in high dimensional systems such as humanoids Yet, given enough compute PPO often caught up. Our follow up paper on on Adaptive Horizon Actor Critic at ICML 2024 discovers the cause and provides a fix. However, we find that even when given ground-truth dynamics, not all gradients are useful due to sample error. 1st-Order Model-Based Reinforcement Learning methods employing differentiable simulation provide gradients with reduced variance but are susceptible to bias in scenarios involving stiff dynamics, such as physical contact. We find that back-propagating through contact and long trajectories drastically reduces gradient accuracy. Using this insight, we propose AHAC to dynamically adapt its roll-out horizon to avoid differentiating through stiff contact. AHAC is a first-order model-based RL algorithm that learns high-dimensional tasks in minutes (wall clock) and outperforms PPO by 40%, even in the limit of data provided to PPO. This work is led by Ignat Georgiev alongside Krishnan Srinivasan, Jie Xu, Eric Heiden and ample assistance from warp team at NVIDIA Robotics (Miles Macklin)show more