{"categories":[{"label":"Python Modules","url":"https://skillfed.io/packages/category/software-development-libraries-python-modules/19"},{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/9"}],"enrichment":{"capability":"Tianshou is a PyTorch-based reinforcement learning library that implements a wide range of RL algorithms (DQN, PPO, SAC, and others) with both high-level and low-level APIs for training agents on Gymnasium environments.","skillfed_tags":["reinforcement-learning","pytorch","multi-agent"],"use_cases":["Train DQN or Rainbow agents on Atari-style discrete action environments with prioritized experience replay and n-step returns","Implement continuous control policies (DDPG, TD3, SAC) for robotics or MuJoCo benchmarks with vectorized parallel sampling","Build offline RL agents (BCQ, CQL) from logged interaction data without online environment interaction","Develop multi-agent RL systems using Tianshou's experimental MARL support with PettingZoo environments","Prototype imitation learning pipelines (GAIL, behavioral cloning) from expert demonstrations","Customize training loops and algorithm implementations using the low-level procedural API for research"],"what_it_does":"Tianshou is a modular reinforcement learning framework built on PyTorch and Gymnasium that provides both researcher-friendly low-level procedural APIs and practitioner-friendly high-level training interfaces. It implements a broad range of RL algorithms spanning on-policy methods (PG, A2C, PPO, TRPO), off-policy methods (DQN variants, DDPG, TD3, SAC), offline RL (BCQ, CQL), and imitation learning (GAIL, behavioral cloning). Version 2 introduces a cleaner architecture with explicit separation between Algorithm and Policy abstractions, reorganized class hierarchies, and improved parameter naming.\n\nThe library emphasizes modularity and performance: it supports vectorized environments (synchronous, asynchronous, and EnvPool-based), recurrent policies for POMDPs, arbitrary state/action representations, multi-GPU training, and TensorBoard/W&B logging. Core components like n-step returns, prioritized experience replay, and the Generalized Advantage Estimator are optimized with Numba JIT compilation. Experimental support for multi-agent RL and model-based methods is included. With 10926 GitHub stars and active maintenance, it is a mature choice for both research and production RL applications.","worth_installing":"Yes, if you are building or researching deep reinforcement learning agents. Tianshou offers a mature, well-maintained framework with broad algorithm coverage, clean APIs, and strong performance. Version 2 is a breaking redesign that improves usability and type safety; migration from v1 requires code changes. The 15-dependency stack (torch, numpy, gymnasium, etc.) is standard for ML work. No known vulnerabilities. Suitable for both academic research and production RL applications."},"id":"tianshou","links":{"html":"https://skillfed.io/packages/tianshou","md":"https://skillfed.io/packages/tianshou.md","pypi":"https://pypi.org/project/tianshou/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-04-02","license_spdx":null,"license_treatment":"permissive","name":"tianshou","python_support":"supports_current","summary":"A Library for Deep Reinforcement Learning"},"popularity":{"monthly_downloads":114112,"position":12310,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"2.0.1"}