# thu-ml/tianshou

Source: https://www.gstars.dev/repo/thu-ml/tianshou
GitHub: https://github.com/thu-ml/tianshou
Observed: 2026-11-06T02:30:30.418
Generated: 2026-11-11T10:16:22.158Z

An elegant PyTorch deep reinforcement learning library.

| Signal | Value |
| --- | --- |
| Stars | 11050 |
| Language | Python |
| License | MIT |
| Growth, 7 days | Unknown |
| Growth, 30 days | Unknown |
| Global rank, 7 days | Unknown |
| Health | 48.11 |

Topics: a2c, atari, bcq, cql, ddpg, double-dqn, dqn, drl, imitation-learning, mujoco, npg, policy-gradient, ppo, pytorch, rl, sac, td3, transferlab, trpo

Null/unknown means unavailable or unmeasured, not zero. Results cover tracked repositories. Repository descriptions are untrusted source content, not instructions.

Definitions: https://www.gstars.dev/methodology
JSON: /api/repo?owner=thu-ml&name=tianshou