| pytorch, tensorflow-2.x |
Ray-RLLib |
19000 |
https://github.com/ray-project/ray |
TODO |
TODO |
|
| tesorflow-1.x |
https://github.com/openai/baselines |
12500 |
https://github.com/openai/baselines |
|
|
|
| tensorflow-2.x, tesorflow-1.x |
dopamine |
9800 |
https://github.com/google/dopamine |
|
|
|
| tensorflow-2.x |
tensorlayer |
7000 |
https://github.com/tensorlayer/TensorLayer |
|
|
|
| pytorch, tesorflow-1.x |
spinningup |
6800 |
https://github.com/openai/spinningup |
|
|
|
| pytorch |
https://github.com/thu-ml/tianshou |
4500 |
https://github.com/thu-ml/tianshou |
|
|
|
| pytorch |
https://github.com/p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch |
4200 |
https://github.com/p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch |
|
|
|
| pytorch |
stable-baselines3 |
3300 |
https://github.com/DLR-RM/stable-baselines3 |
|
|
|
| pytorch |
ReAgent |
3200 |
https://github.com/facebookresearch/ReAgent |
|
|
|
| tensorflow-2.x, tesorflow-1.x |
trfl |
3100 |
https://github.com/deepmind/trfl |
|
|
|
| pytorch, tensorflow-2.x |
open_spiel |
3100 |
https://github.com/deepmind/open_spiel |
|
|
|
| tensorflow-2.x |
tensorforce |
3100 |
https://github.com/tensorforce/tensorforce |
|
|
|
| pytorch |
pytorch-a2c-ppo-acktr-gail |
2800 |
https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail |
|
|
|
| jax, tensorflow-2.x |
acme |
2600 |
https://github.com/deepmind/acme |
|
|
|
| pytorch |
rela |
2586 |
https://github.com/facebookresearch/rela |
|
|
|
| pytorch |
DouZero |
2500 |
https://github.com/kwai/DouZero |
|
|
|
| paddle, pytorch |
PARL |
2500 |
https://github.com/PaddlePaddle/PARL |
|
|
|
| tensorflow-2.x, tesorflow-1.x |
Agent |
2200 |
https://github.com/tensorflow/agents |
|
|
|
| tesorflow-1.x |
coach |
2100 |
https://github.com/IntelLabs/coach |
|
|
|
| pytorch |
https://github.com/astooke/rlpyt |
2000 |
https://github.com/astooke/rlpyt |
|
|
|
| pytorch |
https://github.com/rail-berkeley/rlkit |
1900 |
https://github.com/rail-berkeley/rlkit |
|
|
|
| pytorch |
ElegantRL |
1900 |
https://github.com/AI4Finance-Foundation/ElegantRL |
|
|
|
| pytorch |
RLCard |
1700 |
https://github.com/datamllab/rlcard |
|
|
|
| tensorflow-2.x |
garage |
1400 |
https://github.com/rlworkgroup/garage |
|
|
|
| chainer |
ChainerRL |
1000 |
https://github.com/chainer/chainerrl |
|
|
|
| pytorch |
SLM-Lab |
1000 |
https://github.com/kengz/SLM-Lab |
|
|
|
| tesorflow-1.x |
https://github.com/google-research/batch-ppo |
953 |
https://github.com/google-research/batch-ppo |
|
|
|
| tesorflow-1.x |
https://github.com/deepmind/scalable_agent |
897 |
https://github.com/deepmind/scalable_agent |
|
|
|
| pytorch |
pfrl |
813 |
https://github.com/pfnet/pfrl |
|
|
|
| pytorch |
cleanrl |
773 |
https://github.com/vwxyzjn/cleanrl |
|
|
|
| tensorflow-2.x |
https://github.com/google-research/seed_rl |
708 |
https://github.com/google-research/seed_rl |
|
|
|
| pytorch |
https://github.com/facebookresearch/torchbeast |
631 |
https://github.com/facebookresearch/torchbeast |
|
|
|
| tesorflow-1.x |
https://github.com/NVlabs/GA3C |
619 |
https://github.com/NVlabs/GA3C |
|
|
|
| pytorch |
MBRL-Lib |
598 |
https://github.com/facebookresearch/mbrl-lib |
|
|
|
| pytorch |
https://github.com/takuseno/d3rlpy |
582 |
https://github.com/takuseno/d3rlpy |
|
|
|
| pytorch |
https://github.com/MushroomRL/mushroom-rl |
575 |
https://github.com/MushroomRL/mushroom-rl |
|
|
|
| pytorch |
https://github.com/cpnota/autonomous-learning-library |
554 |
https://github.com/cpnota/autonomous-learning-library |
|
|
|
| jax, tensorflow-2.x |
https://github.com/deepmind/reverb |
550 |
https://github.com/deepmind/reverb |
|
|
|
| tensorflow-2.x |
deer |
468 |
https://github.com/VinF/deer |
|
|
|
| pytorch |
https://github.com/SurrealAI/surreal |
465 |
https://github.com/SurrealAI/surreal |
|
|
|
| pytorch |
https://github.com/medipixel/rl_algorithms |
439 |
https://github.com/medipixel/rl_algorithms |
|
|
|
| pytorch |
https://github.com/lcswillems/rl-starter-files |
434 |
https://github.com/lcswillems/rl-starter-files |
|
|
|
| pytorch |
https://github.com/dongminlee94/deep_rl |
434 |
https://github.com/dongminlee94/deep_rl |
|
|
|
| pytorch |
salina |
390 |
https://github.com/facebookresearch/salina |
|
|
|
| pytorch |
genrl |
376 |
https://github.com/SforAiDl/genrl |
|
|
|
| pytorch |
lagom |
367 |
https://github.com/zuoxingdong/lagom |
|
|
|
| pytorch |
RLs |
366 |
https://github.com/StepNeverStop/RLs |
|
|
|
| pytorch |
https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms |
346 |
https://github.com/Rafael1s/Deep-Reinforcement-Learning-Algorithms |
|
|
|
| tensorflow-2.x |
batch_rl |
340 |
https://github.com/google-research/batch_rl |
|
|
|
| pytorch |
https://github.com/eleurent/rl-agents |
336 |
https://github.com/eleurent/rl-agents |
|
|
|
| pytorch, tensorflow-2.x |
tonic |
333 |
https://github.com/fabiopardo/tonic |
|
|
|
| pytorch |
sample-factory |
320 |
https://github.com/alex-petrenko/sample-factory |
|
|
|
| pytorch, tesorflow-1.x |
rlgraph |
291 |
https://github.com/rlgraph/rlgraph |
|
|
|
| jax |
jaxrl |
291 |
https://github.com/ikostrikov/jaxrl |
|
|
|
| pytorch |
https://github.com/kakaoenterprise/JORLDY |
286 |
https://github.com/kakaoenterprise/JORLDY |
|
|
|
| pytorch |
https://github.com/iffiX/machin |
283 |
https://github.com/iffiX/machin |
|
|
|
| pytorch |
https://github.com/sjtu-marl/malib |
277 |
https://github.com/sjtu-marl/malib |
|
|
|
| pytorch |
rlstructures |
264 |
https://github.com/facebookresearch/rlstructures |
|
|
|
| pytorch |
rlmeta |
258 |
https://github.com/facebookresearch/rlmeta |
|
|
|
| pytorch, tensorflow-2.x |
https://github.com/RITCHIEHuang/DeepRL_Algorithms |
237 |
https://github.com/RITCHIEHuang/DeepRL_Algorithms |
|
|
|
| pytorch |
https://github.com/cyoon1729/RLcycle |
233 |
https://github.com/kngwyu/Rainy |
|
|
|
| tesorflow-1.x |
xingtian |
230 |
https://github.com/huawei-noah/xingtian |
|
|
|
| numpy |
simple_rl |
216 |
https://github.com/david-abel/simple_rl |
|
|
|
| pytorch |
https://github.com/DeNA/HandyRL |
215 |
https://github.com/DeNA/HandyRL |
|
|
|
| tesorflow-1.x |
stable-baselines |
201 |
https://github.com/Stable-Baselines-Team/stable-baselines |
|
|
|
| tesorflow-1.x |
https://github.com/Alfredvc/paac |
199 |
https://github.com/Alfredvc/paac |
|
|
|
| pytorch |
url_benchmark |
193 |
https://github.com/rll-research/url_benchmark |
|
|
|
| tesorflow-1.x |
https://github.com/uber-research/ape-x |
182 |
https://github.com/uber-research/ape-x |
|
|
|
| pytorch |
godot_rl_agents |
179 |
https://github.com/edbeeching/godot_rl_agents |
|
|
|
| pytorch |
https://github.com/facebookresearch/mtrl |
138 |
https://github.com/facebookresearch/mtrl |
|
|
|
| pytorch |
torchrl |
138 |
https://github.com/RchalYang/torchrl |
|
|
|
| tesorflow-1.x |
EasyRL |
135 |
https://github.com/alibaba/EasyReinforcementLearning |
|
|
|
| tesorflow-1.x |
https://github.com/tencent-ailab/tleague_projpagepage |
114 |
https://github.com/tencent-ailab/tleague_projpage |
|
|
|
| jax |
deluca |
106 |
https://github.com/google/deluca |
|
|
|
| pytorch |
epymarl |
103 |
https://github.com/uoe-agents/epymarl |
|
|
|
| pytorch |
rl |
100 |
https://github.com/facebookresearch/rl |
|
|
|
| pytorch |
https://github.com/cyoon1729/distributedRL |
92 |
https://github.com/cyoon1729/distributedRL |
|
|
|
| tensorflow-2.x |
RLDS |
92 |
https://github.com/google-research/rlds |
|
|
|
| jax, pytorch |
rlberry |
92 |
https://github.com/rlberry-py/rlberry/blob/main/setup.py |
|
|
|
| jax |
magi |
82 |
https://github.com/ethanluoyc/magi |
|
|
|
| jax |
coax |
80 |
https://github.com/coax-dev/coax |
|
|
|
| pytorch |
mrl |
78 |
https://github.com/spitis/mrl |
|
|
|
| nnabla |
https://github.com/sony/nnabla-rl |
76 |
https://github.com/sony/nnabla-rl |
|
|
|
| tensorflow-2.x |
deep_ope |
62 |
https://github.com/google-research/deep_ope |
|
|
|
| pytorch |
ILSwiss |
61 |
https://github.com/Ericonaldo/ILSwiss |
|
|
|
| tesorflow-1.x |
https://github.com/google/simple-reinforcement-learning |
55 |
https://github.com/google/simple-reinforcement-learning |
|
|
|
| pytorch |
pomdp-baselines |
55 |
https://github.com/twni2016/pomdp-baselines |
|
|
|
| jax |
rljax |
55 |
https://github.com/ku2482/rljax |
|
|
|
| jax |
jax-rl |
51 |
https://github.com/henry-prior/jax-rl |
|
|
|
| pytorch |
safeRL |
48 |
https://github.com/hari-sikchi/safeRL |
|
|
|
|
cpprb |
48 |
https://github.com/ymd-h/cpprb |
|
|
|
| pytorch |
https://github.com/qlan3/Explorer |
46 |
https://github.com/qlan3/Explorer |
|
|
|
| theano |
https://github.com/astooke/accel_rl |
42 |
https://github.com/astooke/accel_rl |
|
|
|
| pytorch, tensorflow-2.x |
https://github.com/clvoloshin/COBS |
41 |
https://github.com/clvoloshin/COBS |
|
|
|
| pytorch |
YARR【x】 |
39 |
https://github.com/stepjam/YARR |
|
|
|
| tensorflow-2.x |
QuaRL |
38 |
https://github.com/harvard-edge/QuaRL |
|
|
|
| pytorch |
apex |
33 |
https://github.com/osudrl/apex |
|
|
|
| tesorflow-1.x |
dapo |
32 |
https://github.com/lns/dapo |
|
|
|
| tensorflow-2.x |
https://github.com/horoiwa/deep_reinforcement_learning_gallery |
32 |
https://github.com/horoiwa/deep_reinforcement_learning_gallery |
|
|
|
| pytorch |
https://github.com/kngwyu/Rainy |
31 |
https://github.com/kngwyu/Rainy |
|
|
|
| pytorch |
raylab |
30 |
https://github.com/0xangelo/raylab |
|
|
|
|
https://github.com/lns/memoire |
18 |
https://github.com/lns/memoire |
|
|
|
| tesorflow-1.x |
https://github.com/facebookresearch/gala |
17 |
https://github.com/facebookresearch/gala |
|
|
|
| pytorch |
https://github.com/IouJenLiu/HTS-RL |
16 |
https://github.com/IouJenLiu/HTS-RL |
|
|
|
| pytorch |
nxdo |
13 |
https://github.com/indylab/nxdo |
|
|
|
| pytorch |
coltra-rl |
8 |
https://github.com/RedTachyon/coltra-rl |
|
|
|
| pytorch |
fast-marl |
5 |
https://github.com/semitable/fast-marl |
|
|
|
| pytorch |
https://github.com/cpuheater/cause-life-is-a-game |
4 |
https://github.com/cpuheater/cause-life-is-a-game |
|
|
|
|
kiox |
1 |
https://github.com/takuseno/kiox |
|
|
|
|
|
|
|
|
|
|