awesome-reinforcement-learning-lib
GitHub's code repository is all you need
https://github.com/wwxFromTju/awesome-reinforcement-learning-lib
Last synced: 3 days ago
JSON representation
-
RL Library
-  | [ray-rllib](https://github.com/ray-project/ray/) | pytorch, tensorflow-2.x |
-  | tesorflow-1.x |
-  | tensorflow-2.x |
-  | [tianshou](https://github.com/thu-ml/tianshou/) | pytorch |
-  | [keras-rl](https://github.com/keras-rl/keras-rl/) | keras |
-  | [stable-baselines3](https://github.com/DLR-RM/stable-baselines3/) | pytorch |
-  | [Deep-Reinforcement-Learning-Algorithms-with-PyTorch](https://github.com/p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch/) | pytorch |
-  | pytorch, tensorflow-2.x |
-  | pytorch |
-  | pytorch |
-  | tensorflow-2.x |
-  | jax, tensorflow-2.x |
-  | [pytorch-a2c-ppo-acktr-gail](https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail/) | pytorch |
-  | tensorflow-2.x, tesorflow-1.x |
-  | paddle, pytorch |
-  | [ElegantRL](https://github.com/AI4Finance-Foundation/ElegantRL/) | pytorch |
-  | tensorflow-2.x, tesorflow-1.x |
-  | [DI-engine](https://github.com/opendilab/DI-engine/) | pytorch |
-  | tensorflow-2.x, tesorflow-1.x |
-  | pytorch, tesorflow-1.x |
-  | pytorch |
-  | tesorflow-1.x |
-  | pytorch |
-  | pytorch |
-  | [rlkit](https://github.com/rail-berkeley/rlkit/) | pytorch |
-  | tensorflow-2.x |
-  | [SLM-Lab](https://github.com/kengz/SLM-Lab/) | pytorch |
-  | chainer |
-  | pytorch |
-  | pytorch |
-  | jax |
-  | [batch-ppo](https://github.com/google-research/batch-ppo/) | tesorflow-1.x |
-  | tesorflow-1.x |
-  | pytorch |
-  | [seed_rl](https://github.com/google-research/seed_rl/) | tensorflow-2.x |
-  | [mbrl-lib](https://github.com/facebookresearch/mbrl-lib/) | pytorch |
-  | pytorch |
-  | [mushroom-rl](https://github.com/MushroomRL/mushroom-rl/) | pytorch |
-  | jax, tensorflow-2.x |
-  | tesorflow-1.x |
-  | [autonomous-learning-library](https://github.com/cpnota/autonomous-learning-library/) | pytorch |
-  | [CORL](https://github.com/tinkoff-ai/CORL/) | pytorch |
-  | pytorch |
-  | pytorch |
-  | pytorch |
-  | jax |
-  | [Deep-Reinforcement-Learning-Algorithms](https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms/) | pytorch |
-  | [rl-agents](https://github.com/eleurent/rl-agents/) | pytorch |
-  | [batch_rl](https://github.com/google-research/batch_rl/) | tensorflow-2.x |
-  | pytorch |
-  | pytorch |
-  | pytorch |
-  | pytorch |
-  | pytorch |
-  | [sample-factory](https://github.com/alex-petrenko/sample-factory/) | pytorch |
-  | [rl-starter-files](https://github.com/lcswillems/rl-starter-files/) | pytorch |
-  | tensorflow-2.x |
-  | pytorch, tensorflow-2.x |
-  | pytorch |
-  | [malib](https://github.com/sjtu-marl/malib/) | pytorch |
-  | pytorch |
-  | pytorch |
-  | pytorch, tesorflow-1.x |
-  | pytorch |
-  | [url_benchmark](https://github.com/rll-research/url_benchmark/) | pytorch |
-  | [epymarl](https://github.com/uoe-agents/epymarl/) | pytorch |
-  | [xingtian](https://github.com/huawei-noah/xingtian/) | tesorflow-1.x |
-  | pytorch |
-  | pytorch |
-  | pytorch, tensorflow-2.x |
-  | [pymdp](https://github.com/infer-actively/pymdp/) | numpy |
-  | [stable-baselines](https://github.com/Stable-Baselines-Team/stable-baselines/) | tesorflow-1.x |
-  | [simple_rl](https://github.com/david-abel/simple_rl/) | numpy |
-  | pytorch, Tensorflow 2.1 |
-  | [tmrl](https://github.com/trackmania-rl/tmrl/) | pytorch |
-  | tesorflow-1.x |
-  | pytorch |
-  | [pomdp-baselines](https://github.com/twni2016/pomdp-baselines/) | pytorch |
-  | pytorch |
-  | tesorflow-1.x |
-  | pytorch |
-  | pytorch |
-  | [skrl](https://github.com/Toni-SM/skrl/) | pytorch |
-  | [ape-x](https://github.com/uber-research/ape-x/) | tesorflow-1.x |
-  | [rlds](https://github.com/google-research/rlds/) | tensorflow-2.x |
-  | [coax](https://github.com/coax-dev/coax/) | jax |
-  | jax |
-  | [tleague_projpage](https://github.com/tencent-ailab/tleague_projpage/) | tesorflow-1.x |
-  | [rlberry](https://github.com/rlberry-py/rlberry/) | jax, pytorch |
-  | pytorch |
-  | [nnabla-rl](https://github.com/sony/nnabla-rl/) | nnabla |
-  | [d4pg-pytorch](https://github.com/schatty/d4pg-pytorch/) | pytorch |
-  | jax |
-  | pytorch |
-  | [DB-Football](https://github.com/Shanghai-Digital-Brain-Laboratory/DB-Football) | pytorch |
-  | pytorch |
-  | pytorch |
-  | jax |
-  | pytorch |
-  | [RLHive](https://github.com/chandar-lab/RLHive/) | torch |
-  | [deep_ope](https://github.com/google-research/deep_ope/) | tensorflow-2.x |
-  | jax |
-  | pytorch |
-  | tensorflow-2.x |
-  | [jax-rl](https://github.com/henry-prior/jax-rl/) | jax |
-  | tensorflow-2.x |
-  | [cpprb](https://github.com/ymd-h/cpprb/) | |
-  | [simple-reinforcement-learning](https://github.com/google/simple-reinforcement-learning/) | tesorflow-1.x |
-  | [safeRL](https://github.com/hari-sikchi/safeRL/) | pytorch |
-  | pytorch |
-  | pytorch, tensorflow-2.x |
-  | pytorch |
-  | jax, pytorch |
-  | [QuaRL](https://github.com/harvard-edge/QuaRL/) | tensorflow-2.x |
-  | theano |
-  | pytorch |
-  | tesorflow-1.x |
-  | pytorch |
-  | [gymnax-blines](https://github.com/RobertTLange/gymnax-blines/) | jax |
-  | pytorch |
-  | pytorch |
-  | tesorflow-1.x |
-  | [coltra-rl](https://github.com/RedTachyon/coltra-rl/) | pytorch |
-  | [HTS-RL](https://github.com/IouJenLiu/HTS-RL/) | pytorch |
-  | |
-  | [xpag](https://github.com/perrin-isir/xpag/) | jax |
-  | tensorflow |
-  | pytorch |
-  | [fast-marl](https://github.com/semitable/fast-marl/) | pytorch |
-  | [haiku-baseline](https://github.com/TinkTheBoush/haiku-baseline/) | jax |
-  | [reinforcement](https://github.com/mindspore-ai/reinforcement/) | mindspore |
-  | jax |
-  | tf-2.x |
-  | [reinforced-lib](https://github.com/m-wojnar/reinforced-lib/) | jax |
-  | tensorflow-1.x |
-  | [cause-life-is-a-game](https://github.com/cpuheater/cause-life-is-a-game/) | pytorch |
-  | [causal-mbrl](https://github.com/FrankTianTT/causal-mbrl/) | pytorch |
-  | [mbrl-jax](https://github.com/kchua/mbrl-jax/) | jax |
-  | pytorch |
-
RL Accelerated Environment
- [1
- ](https://arxiv.org/abs/2206.10558) |  | [EnvPool](https://github.com/sail-sg/envpool/) | cpp | Atari, Mujoco, Compilable environment |
-  |  | [ELF](https://github.com/facebookresearch/ELF/) | cpp | Game in cpp, MiniRTS |
-  |  | [Cule](https://github.com/NVlabs/cule/) | gpu | Atari |
-  |  | [Brax](https://github.com/google/brax/) | gpu | robot |
- ](https://arxiv.org/abs/2108.10470) |  | [Isaac-gym](https://github.com/NVIDIA-Omniverse/IsaacGymEnvs/) | gpu | robot |
- ](https://arxiv.org/abs/2108.13976) |  | [WarpDrive](https://github.com/salesforce/warp-drive/) | gpu | multiagent |
-  | cpp | grid-world game |
-  | gpu | physics lightweight simulation environment |
-  | jit+xla | Game / Combinatorial |
Categories
Sub Categories