OpenAI Blog
May 16, 2017
Robots that learn
We’ve created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once.
Meta-learning for wrestling
We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent, and also show that the meta-learning agent can adapt to physical malfunction.
Related stories
arXiv AI
Jul 22
The Open Ant: A Robot Platform for Reinforcement Learning Research
arXiv:2607. 18488v1 Announce Type: cross Abstract: Reinforcement learning (RL) research has demonstrated success in both physical and simulated domains; however, the predominant methodology remains rooted in simulations.
arXiv AI
Jun 19
Playful Agentic Robot Learning
arXiv:2606. 19419v1 Announce Type: cross Abstract: Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions.
arXiv Machine Learning
Jun 8
Robotic Policy Adaptation via Weight-Space Meta-Learning
arXiv:2606. 07217v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are emerging as a promising paradigm for robotic manipulation, enabling general-purpose policies trained from large corpora of demonstrations and action labels.
arXiv AI
Jul 2
Coachable agents for interactive gameplay
arXiv:2607. 00642v1 Announce Type: new Abstract: Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing to robotics to foundation models.
arXiv AI
Jul 24
What Matters for Simulation to Online Reinforcement Learning on Real Robots
arXiv:2602. 20220v2 Announce Type: replace-cross Abstract: We investigate what specific design choices enable successful online reinforcement learning (RL) on physical robots.
arXiv AI
Jun 19
Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning
arXiv:2605. 22748v2 Announce Type: replace-cross Abstract: Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces.
arXiv Statistics ML
2d ago
Meta-reinforcement learning with minimum attention
arXiv:2505.16741v5 Announce Type: replace-cross Abstract: Minimum attention applies the least action principle in changes of control concerning state and time, first proposed by Brockett. The involve...
arXiv AI
Jul 23
You Live More Than Once: Towards Hierarchical Skill Meta-Evolving
arXiv:2605. 28390v2 Announce Type: replace Abstract: Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems.
arXiv AI
Aug 19
Teach and Grow: An Agent-Centered Architecture for General Robot Learning
Teach-and-Grow Learning (TGL) is an agent-centered architecture that transforms a few successful demonstrations into reusable Skill Blocks, enabling a robot to compose, execute, and revise behaviors in new scenes without task-specific policy retraining. The system maintains a Skill Library and structured Experience Memory to capture successes, failures, and repairs, allowing persistent reuse and agent-directed adaptation. Evaluation on the LIBERO benchmark shows state-of-the-art performance, and the authors propose a scaling-law hypothesis suggesting that accumulated reusable experience reduces future-task error and teaching demand following a power-law trend.
arXiv Machine Learning
Sep 15
Safe Meta-Reinforcement Learning via Information Space Reachability
arXiv:2609.15915v1 Announce Type: new Abstract: Meta-reinforcement learning (meta-RL) enables agents to adapt to unseen tasks with limited experience. Despite its promise, the application of meta-RL...
arXiv Machine Learning
Aug 24
A Deep Reinforcement Learning Framework for Closed-loop Guidance of Fish Schools via Virtual Agents
arXiv:2603.28200v2 Announce Type: replace-cross Abstract: Guiding collective motion in biological groups is a fundamental challenge in understanding social interaction rules. In this study, we propos...