OpenAI Blog
Jul 30, 2018
Learning dexterity
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
Solving Rubik’s Cube with a robot hand
We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand. The neural networks are trained entirely in simulation, using the same reinforcement learning code as OpenAI Five paired with a new technique called Automatic Domain Randomization (ADR).
Related stories
arXiv Machine Learning
Jun 29
Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience
arXiv:2606. 27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations.
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 Machine Learning
Jul 7
Scalable Dexterous Robot Learning with AR-based Remote Human-Robot Interactions
arXiv:2602. 07341v2 Announce Type: replace Abstract: This paper focuses on the scalable robot learning for manipulation in the dexterous robot arm-hand systems, where the remote human-robot interactions via augmented reality (AR) are established to collect the expert demonstration data for improving efficiency.
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.
Hugging Face Trending Papers
Jul 13
A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation
Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kinematic references, then train policies via reinforcement learning (RL) to track them. But how does this recipe transfer to dexterous manipulation?
arXiv AI
Jun 9
EgoAERO: Learning Dexterous Manipulation from a Single Egocentric Video without Object Assets
arXiv:2606. 08057v1 Announce Type: cross Abstract: Egocentric RGB-D videos offer a natural source of human dexterous manipulation demonstrations, but existing data is difficult to use for robot learning because object pose, geometry, and contact information are often missing or require pre-scanned object assets.
arXiv Machine Learning
Jun 29
Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions
arXiv:2505. 05517v3 Announce Type: replace-cross Abstract: Functional grasping is essential for enabling dexterous multi-finger robot hands to manipulate objects effectively.
arXiv AI
23h ago
Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Vision
arXiv:2608. 17628v1 Announce Type: cross Abstract: Developing robots capable of understanding and manipulating objects requires compact, interpretable, and generalizable representations.
arXiv Machine Learning
Aug 12
Learning in ImaginationLand: Omnidirectional Policies through 3D Generative Models (OP-Gen)
arXiv:2509. 06191v2 Announce Type: replace-cross Abstract: Recent 3D generative models, which are capable of generating full object shapes from just a few images, now open up new opportunities in robotics.
arXiv Machine Learning
Jul 2
From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
arXiv:2603. 10263v2 Announce Type: replace-cross Abstract: We introduce Distribution Contractive Reinforcement Learning (DICE-RL), a framework that uses reinforcement learning (RL) as a "distribution contraction" operator to refine pretrained generative robot policies.
OpenAI Blog
Jul 4, 2018
Learning Montezuma’s Revenge from a single demonstration
We’ve trained an agent to achieve a high score of 74,500 on Montezuma’s Revenge from a single human demonstration, better than any previously published result. Our algorithm is simple: the agent plays a sequence of games starting from carefully chosen states from the demonstration, and learns from them by optimizing the game score using PPO, the same reinforcement learning algorithm that underpins OpenAI Five.