package owl-rllib
Build not yet checked sectionYPositions = computeSectionYPositions($el), 10)"
x-init="setTimeout(() => sectionYPositions = computeSectionYPositions($el), 10)"
>
On This Page
Reinforcement learning on top of the Owl numerical library
Install
dune-project
Dependency
Authors
Maintainers
Sources
owl-rllib-0.1.tbz
sha256=7f21880386e8dfad71fa7be32819e437b0e555db6ef4fb457f6824ec516422d8
sha512=f49617d1f6faee0b3e32cef9565879503836b46a6eb130513f63cc598d0669fbaa8c535b43070be3cc281abbe19047e6a547fec713058f02194a519818623347
doc/index.html
owl-rllib
Reinforcement learning on top of Owl.
The package has three libraries:
owl-rllib(Owl_rllib): MDPs, tabular methods and dynamic programming; classic control environments; DQN, REINFORCE, A2C and PPO.owl-rllib.llm(Owl_rllib_llm): RL for language models on a toy model (REINFORCE, RLOO, token-level PPO, GRPO and its variants).owl-rllib.bridges(Owl_rllib_bridges): Gymnasium and VizDoom environments, run in a Python child process.
Where to start
- Environments:
Owl_rllib.Ndenv(array observations),Owl_rllib.Env(tabular),Owl_rllib.Vec_env;Owl_rllib.Cartpoleand the other classic control tasks. - Algorithms:
Owl_rllib.Dp,Owl_rllib.Tabular,Owl_rllib.Dqn,Owl_rllib.Reinforce,Owl_rllib.A2c,Owl_rllib.Ppo. - Networks and policies:
Owl_rllib.Neural,Owl_rllib.Policy. - Reproducibility:
Owl_rllib.Rng.
Most modules are functors over Owl's single (S) or double (D) precision, with S and D instances provided. The programs in examples/ show each part in use.
sectionYPositions = computeSectionYPositions($el), 10)"
x-init="setTimeout(() => sectionYPositions = computeSectionYPositions($el), 10)"
>
On This Page