We’re releasing the public beta of OpenAI Gym, a toolkit for developing and comparing reinforcement learning (RL) algorithms. It consists of a growing suite of environments (from simulated robots to Atari games), and a site for comparing and reproducing results.
We’re open-sourcing OpenAI Baselines, our internal effort to reproduce reinforcement learning algorithms with performance on par with published results. We’ll release the algorithms over upcoming months; today’s release includes DQN and three of its variants.
We are releasing Roboschool: open-source software for robot simulation, integrated with OpenAI Gym.
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.
We’re releasing an API for accessing new AI models developed by OpenAI.
arXiv:2607. 07029v1 Announce Type: cross Abstract: Reinforcement learning (RL) policies can be unsafe and vulnerable to attacks.
We’re releasing Safety Gym, a suite of environments and tools for measuring progress towards reinforcement learning agents that respect safety constraints while training.
We hosted the first OpenAI Robotics Symposium on April 27, 2019.
We’re releasing the full version of Gym Retro, a platform for reinforcement learning research on games. This brings our publicly-released game count from around 70 Atari games and 30 Sega games to over 1,000 games across a variety of backing emulators.
arXiv:2607. 05773v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents, traditional static evaluation fails to capture multi-step decision-making.
Learn how OpenAI uses AI to enhance support, cutting response times, improving quality, and scaling to meet hypergrowth.
arXiv:2603. 27450v2 Announce Type: replace Abstract: Thanks to their remarkable flexibility, diffusion models and flow models have emerged as promising candidates for policy representation.
arXiv:2602. 20220v2 Announce Type: replace-cross Abstract: We investigate what specific design choices enable successful online reinforcement learning (RL) on physical robots.