owl-rllibversion Documentation on ocaml.org
Reinforcement learning on top of the Owl numerical library
Tabular methods, dynamic programming, DQN, REINFORCE, A2C and PPO on Owl's neural networks, classic control environments checked against Gymnasium, RL algorithms for language-model fine-tuning (REINFORCE, RLOO, PPO, GRPO and its variants) on a toy model, and an optional bridge to Gymnasium and VizDoom running in a Python child process.
| Tags | reinforcement-learning machine-learning owl |
|---|---|
| Author | Jianxin Zhao |
| License | MIT |
| Published | |
| Homepage | https://github.com/owlbarn/owl-rllib |
| Issue Tracker | https://github.com/owlbarn/owl-rllib/issues |
| Maintainer | Jianxin Zhao |
| Dependencies | |
| Source [http] | https://github.com/owlbarn/owl-rllib/releases/download/0.1/owl-rllib-0.1.tbz sha256=7f21880386e8dfad71fa7be32819e437b0e555db6ef4fb457f6824ec516422d8 sha512=f49617d1f6faee0b3e32cef9565879503836b46a6eb130513f63cc598d0669fbaa8c535b43070be3cc281abbe19047e6a547fec713058f02194a519818623347 |
| Edit | https://github.com/ocaml/opam-repository/tree/master/packages/owl-rllib/owl-rllib.0.1/opam |
No package is dependent


