Awesome Reinforcement Learning Library
RL Library
| Star | Last Update | Name | Backend |
|---|---|---|---|
 |
 |
ray-rllib | pytorch, tensorflow-2.x |
 |
 |
baselines | tesorflow-1.x |
 |
 |
dopamine | tensorflow-2.x, tesorflow-1.x |
 |
 |
spinningup | pytorch, tesorflow-1.x |
 |
 |
TensorLayer | tensorflow-2.x |
 |
 |
tianshou | pytorch |
 |
 |
keras-rl | keras |
 |
 |
stable-baselines3 | pytorch |
 |
 |
Deep-Reinforcement-Learning-Algorithms-with-PyTorch | pytorch |
 |
 |
open_spiel | pytorch, tensorflow-2.x |
 |
 |
ReAgent | pytorch |
 |
 |
DouZero | pytorch |
 |
 |
tensorforce | tensorflow-2.x |
 |
 |
acme | jax, tensorflow-2.x |
 |
 |
pytorch-a2c-ppo-acktr-gail | pytorch |
 |
 |
trfl | tensorflow-2.x, tesorflow-1.x |
 |
 |
PARL | paddle, pytorch |
 |
 |
ElegantRL | pytorch |
 |
 |
agents | tensorflow-2.x, tesorflow-1.x |
 |
 |
DI-engine | pytorch |
 |
 |
cleanrl | pytorch |
 |
 |
coach | tesorflow-1.x |
 |
 |
rlcard | pytorch |
 |
 |
rlkit | pytorch |
 |
 |
rlpyt | pytorch |
 |
 |
garage | tensorflow-2.x |
 |
 |
SLM-Lab | pytorch |
 |
 |
chainerrl | chainer |
 |
 |
rl | pytorch |
 |
 |
pfrl | pytorch |
 |
 |
rlax | jax |
 |
 |
batch-ppo | tesorflow-1.x |
 |
 |
scalable_agent | tesorflow-1.x |
 |
 |
d3rlpy | pytorch |
 |
 |
seed_rl | tensorflow-2.x |
 |
 |
mbrl-lib | pytorch |
 |
 |
torchbeast | pytorch |
 |
 |
mushroom-rl | pytorch |
 |
 |
reverb | jax, tensorflow-2.x |
 |
 |
GA3C | tesorflow-1.x |
 |
 |
autonomous-learning-library | pytorch |
 |
 |
CORL | pytorch |
 |
 |
sample-factory | pytorch |
 |
 |
rl-starter-files | pytorch |
 |
 |
deer | tensorflow-2.x |
 |
 |
surreal | pytorch |
 |
 |
rl_algorithms | pytorch |
 |
 |
deep_rl | pytorch |
 |
 |
jaxrl | jax |
 |
 |
Deep-Reinforcement-Learning-Algorithms | pytorch |
 |
 |
rl-agents | pytorch |
 |
 |
batch_rl | tensorflow-2.x |
 |
 |
RLs | pytorch |
 |
 |
salina | pytorch |
 |
 |
rl_games | pytorch |
 |
 |
godot_rl_agents | pytorch |
 |
 |
genrl | pytorch |
 |
 |
tonic | pytorch, tensorflow-2.x |
 |
 |
lagom | pytorch |
 |
 |
malib | pytorch |
 |
 |
machin | pytorch |
 |
 |
JORLDY | pytorch |
 |
 |
rlgraph | pytorch, tesorflow-1.x |
 |
 |
rlmeta | pytorch |
 |
 |
url_benchmark | pytorch |
 |
 |
epymarl | pytorch |
 |
 |
xingtian | tesorflow-1.x |
 |
 |
HandyRL | pytorch |
 |
 |
rlstructures | pytorch |
 |
 |
DeepRL_Algorithms | pytorch, tensorflow-2.x |
 |
 |
pymdp | numpy |
 |
 |
stable-baselines | tesorflow-1.x |
 |
 |
simple_rl | numpy |
 |
 |
alf | pytorch, Tensorflow 2.1 |
 |
 |
tmrl | pytorch |
 |
 |
paac | tesorflow-1.x |
 |
 |
adeptRL | pytorch |
 |
 |
pomdp-baselines | pytorch |
 |
 |
skrl | pytorch |
 |
 |
ape-x | tesorflow-1.x |
 |
 |
mtrl | pytorch |
 |
 |
EasyReinforcementLearning | tesorflow-1.x |
 |
 |
torchrl | pytorch |
 |
 |
TimeChamber | pytorch |
 |
 |
rlds | tensorflow-2.x |
 |
 |
coax | jax |
 |
 |
tleague_projpage | tesorflow-1.x |
 |
 |
rlberry | jax, pytorch |
 |
 |
ILSwiss | pytorch |
 |
 |
deluca | jax |
 |
 |
nnabla-rl | nnabla |
 |
 |
d4pg-pytorch | pytorch |
 |
 |
magi | jax |
 |
 |
mrl | pytorch |
 |
 |
rsl_rl | pytorch |
 |
 |
distributedRL | pytorch |
 |
 |
sbx | jax |
 |
 |
rela | pytorch |
 |
 |
RLHive | torch |
 |
 |
deep_ope | tensorflow-2.x |
 |
 |
rljax | jax |
 |
 |
Explorer | pytorch |
 |
 |
unstable_baselines | tensorflow-2.x |
 |
 |
jax-rl | jax |
 |
 |
deep_reinforcement_learning_gallery | tensorflow-2.x |
 |
 |
cpprb | |
 |
 |
simple-reinforcement-learning | tesorflow-1.x |
 |
 |
safeRL | pytorch |
 |
 |
YARR | pytorch |
 |
 |
COBS | pytorch, tensorflow-2.x |
 |
 |
DB-Football | pytorch |
 |
 |
raylab | pytorch |
 |
 |
fastpbrl | jax, pytorch |
 |
 |
QuaRL | tensorflow-2.x |
 |
 |
accel_rl | theano |
 |
 |
apex | pytorch |
 |
 |
embodied | tensorflow |
 |
 |
Rainy | pytorch |
 |
 |
dapo | tesorflow-1.x |
 |
 |
abcdrl | pytorch |
 |
 |
gymnax-blines | jax |
 |
 |
MARS | pytorch |
 |
 |
nxdo | pytorch |
 |
 |
gala | tesorflow-1.x |
 |
 |
coltra-rl | pytorch |
 |
 |
HTS-RL | pytorch |
 |
 |
memoire | |
 |
 |
xpag | jax |
 |
 |
fast-marl | pytorch |
 |
 |
haiku-baseline | jax |
 |
 |
reinforcement | mindspore |
 |
 |
sb3_jax | jax |
 |
 |
exarl | tf-2.x |
 |
 |
reinforced-lib | jax |
 |
 |
reproduceRL | tensorflow-1.x |
 |
 |
cause-life-is-a-game | pytorch |
 |
 |
mbrl-jax | jax |
 |
 |
XuanJing | pytorch |
 |
 |
causal-mbrl | pytorch |
RL Accelerated Environment
| Star | arXiv | Last Update | Name | Accelerate Type | Property |
|---|---|---|---|---|---|
| / | / | / | vec_env | subproc [1] [2] | all |
 |
 |
 |
EnvPool | cpp | Atari, Mujoco, Compilable environment |
 |
 |
 |
ELF | cpp | Game in cpp, MiniRTS |
 |
 |
 |
Cule | gpu | Atari |
 |
 |
 |
Brax | gpu | robot |
 |
 |
 |
Isaac-gym | gpu | robot |
 |
 |
 |
WarpDrive | gpu | multiagent |
 |
/ |  |
griddly | cpp | grid-world game |
 |
/ |  |
powderworld | gpu | physics lightweight simulation environment |
 |
/ |  |
jumanji | jit+xla | Game / Combinatorial |