MuJoCo is a physics engine which can do very detailed efficient simulations with contacts. This library lets you use MuJoCo from Python.
This package contains implementations of various RL algorithms for continuous control tasks simulated with MuJoCo.
This project is an AI research implementation library and machine learning research repository. It provides a collection of reference code, illustrative implementations, and open-source research datasets used to verify hypotheses and build upon existing models in artificial intelligence. The repository focuses on scientific research reproduction by translating theoretical findings from published papers into executable code. It includes specialized scientific simulation environments designed to test the behavior of autonomous agents and models within controlled settings. The project covers AI
D4RL is an open-source benchmark for offline reinforcement learning. It provides standardized environments and datasets for training and benchmarking algorithms. A supplementary whitepaper and website are also available.
Principalele funcționalități ale rail-berkeley/d4rl sunt: Datasets and Benchmarks, Reinforcement Learning Environments, World Models, Environment Benchmarks.
Alternativele open-source pentru rail-berkeley/d4rl includ: openai/mujoco-py — MuJoCo is a physics engine which can do very detailed efficient simulations with contacts. This library lets you use… maximecb/gym-minigrid — Simple and easily configurable grid world environments for reinforcement learning. danijar/crafter — Status: Stable release. deepmind/deepmind-research — This project is an AI research implementation library and machine learning research repository. It provides a… aravindr93/mjrl — This package contains implementations of various RL algorithms for continuous control tasks simulated with MuJoCo. farama-foundation/metaworld — Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning.