780 dependents
| Package | Description | Downloads/month |
|---|---|---|
| 🌎💪 BrowserGym, a Gym environment for web task automation | 1.6M | |
| PyTorch version of Stable Baselines, reliable implementations of reinforcement l... | 1.2M | |
| An API standard for multi-agent reinforcement learning environments, with popula... | 338K | |
| An API conversion tool for popular external reinforcement learning environments | 335K | |
| 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning | 204K | |
| A Python library for defining, testing, and using reward functions | 144K | |
| Kaggle Environments | 87K | |
| An elegant PyTorch deep reinforcement learning library. | 84K | |
| Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NV... | 73K | |
| Simple and easily configurable grid world environments for reinforcement learni... | 64K | |
| A gym environment for ALOHA | 61K | |
| TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextua... | 58K | |
| A collection of wrappers for Gymnasium and PettingZoo environments (being merged... | 49K | |
| RL Environments in JAX 🌍 | 48K | |
| A collection of robotics simulation environments for reinforcement learning | 41K | |
| This is an unofficial, use-at-your-own risks port of the webarena benchmark, for... | 34K | |
| This is an unofficial, use-at-your-own risks port of the visualwebarena benchmar... | 33K | |
| Poke-env: Python Interface for Pokemon Showdown Bots | 31K | |
| A benchmark for offline goal-conditioned RL and offline RL | 30K | |
| A standard format for offline reinforcement learning datasets, with popular refe... | 27K | |
| Collections of robotics environments geared towards benchmarking multi-task and ... | 27K | |
| Dopamine is a research framework for fast prototyping of reinforcement learning ... | 26K | |
| A fast grid-based open-ended MARL environment | 25K | |
| BrowserGym integration for the WebLINX benchmark | 23K | |
| A gymnasium environment for PushT. | 23K | |
| Benchmarking Knowledge Transfer in Lifelong Robot Learning | 23K | |
| SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics si... | 22K | |
| ViZDoom is Doom-based AI Research Platform for Reinforcement Learning from Raw V... | 17K | |
| ⚡⚡ Lightning Fast (~300TPS) Reinforcement Learning environment on latest Minecra... | 17K | |
| C++-based high-performance parallel environment execution engine (vectorized env... | 16K | |
| Isaac Lab | 14K | |
| the Composabl core functionality required to apply the Machine Teaching paradigm | 14K | |
| AgileRL is a deep reinforcement learning library focused on improving RL develop... | 14K | |
| the Amesa core functionality required to apply the Machine Teaching paradigm | 14K | |
| Multi-objective Gymnasium environments for reinforcement learning | 13K | |
| Human in the loop Reinforcement Learning suite | 11K | |
| UAV Flight Simulator for Reinforcement Learning Research | 9K | |
| Autonomous training loop for any sequential learning model — PPO, DQN, SAC, TD3,... | 9K | |
| A minimalist environment for decision-making in autonomous driving | 9K | |
| Musculoskeletal environments simulated in MuJoCo | 9K | |
| Implementation of π₀, the robotic foundation model architecture proposed by Phys... | 9K | |
| A diverse suite of scalable reinforcement learning environments in JAX | 9K | |
| The NetHack Learning Environment | 8K | |
| the Composabl core functionality required to apply the Machine Teaching paradigm | 8K | |
| SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics si... | 8K | |
| Flexible reinforcement learning models instantiators library | 8K | |
| Materials for Deep Learning – ÚFAL course NPFL138 | 7K | |
| [JMLR (CCF-A)] PyPop7: A Pure-PYthon LibrarY for POPulation-based Black-Box Opti... | 7K | |
| A research platform to develop automated security policies using quantitative me... | 7K | |
| Benchmarks for automated engineering design | 7K |
