Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -35,10 +35,11 @@ If you want to contact us & join us, you can βοΈ to our team : <opendilab@p
|
|
35 |
| :-------------: | :-------------: | :-------------: | :------------------------: | :------------: | :--------------: | :------------: | :------------------: | :---------: | :---------: | :---------: |
|
36 |
| [PPO](https://arxiv.org/pdf/1707.06347.pdf) | [β
](https://huggingface.co/OpenDILabCommunity/Lunarlander-v2-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/LunarLanderContinuous-v2-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/BipedalWalker-v3-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/Pendulum-v1-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/SpaceInvadersNoFrameskip-v4-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/Hopper-v3-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/HalfCheetah-v3-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-PPO) |
|
37 |
| [DQN](https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf) | [β
](https://huggingface.co/OpenDILabCommunity/Lunarlander-v2-DQN) | π | π | π | [β
](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-DQN) | [β
](https://huggingface.co/OpenDILabCommunity/SpaceInvadersNoFrameskip-v4-DQN) | [β
](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-DQN) | π | π | π |
|
38 |
-
| [C51](https://arxiv.org/
|
39 |
| [DDPG](https://arxiv.org/pdf/1509.02971.pdf) | π | [β
](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-DDPG) | [β
](https://huggingface.co/OpenDILabCommunity/BipedalWalker-v3-DDPG) | [β
](https://huggingface.co/OpenDILabCommunity/Pendulum-v1-DDPG) | π | π | π | [β
](https://huggingface.co/OpenDILabCommunity/Hopper-v3-DDPG) | [β
](https://huggingface.co/OpenDILabCommunity/HalfCheetah-v3-DDPG) | [β
](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-DDPG) |
|
40 |
| [TD3](https://arxiv.org/pdf/1802.09477.pdf) | π | [β
](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-TD3) | [β
](https://huggingface.co/OpenDILabCommunity/BipedalWalker-v3-TD3) | [β
](https://huggingface.co/OpenDILabCommunity/Pendulum-v1-TD3) | π | π | π |[β
](https://huggingface.co/OpenDILabCommunity/Hopper-v3-TD3) | [β
](https://huggingface.co/OpenDILabCommunity/HalfCheetah-v3-TD3) | [β
](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-TD3) |
|
41 |
| [SAC](https://arxiv.org/pdf/1801.01290.pdf) | π | [β
](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-SAC) | [β
](https://huggingface.co/OpenDILabCommunity/BipedalWalker-v3-SAC) | [β
](https://huggingface.co/OpenDILabCommunity/Pendulum-v1-SAC) | π | π | π | [β
](https://huggingface.co/OpenDILabCommunity/Hopper-v3-SAC) | [β
](https://huggingface.co/OpenDILabCommunity/HalfCheetah-v3-SAC) | [β
](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-SAC) |
|
|
|
42 |
|
43 |
</details>
|
44 |
|
|
|
35 |
| :-------------: | :-------------: | :-------------: | :------------------------: | :------------: | :--------------: | :------------: | :------------------: | :---------: | :---------: | :---------: |
|
36 |
| [PPO](https://arxiv.org/pdf/1707.06347.pdf) | [β
](https://huggingface.co/OpenDILabCommunity/Lunarlander-v2-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/LunarLanderContinuous-v2-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/BipedalWalker-v3-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/Pendulum-v1-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/SpaceInvadersNoFrameskip-v4-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/Hopper-v3-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/HalfCheetah-v3-PPO) | [β
](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-PPO) |
|
37 |
| [DQN](https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf) | [β
](https://huggingface.co/OpenDILabCommunity/Lunarlander-v2-DQN) | π | π | π | [β
](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-DQN) | [β
](https://huggingface.co/OpenDILabCommunity/SpaceInvadersNoFrameskip-v4-DQN) | [β
](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-DQN) | π | π | π |
|
38 |
+
| [C51](https://arxiv.org/pdf/1707.06887.pdf) | [β
](https://huggingface.co/OpenDILabCommunity/Lunarlander-v2-C51) | π | π | π | [β
](https://huggingface.co/OpenDILabCommunity/PongNoFrameskip-v4-C51) | [β
](https://huggingface.co/OpenDILabCommunity/SpaceInvadersNoFrameskip-v4-C51) | [β
](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-C51) | π | π | π |
|
39 |
| [DDPG](https://arxiv.org/pdf/1509.02971.pdf) | π | [β
](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-DDPG) | [β
](https://huggingface.co/OpenDILabCommunity/BipedalWalker-v3-DDPG) | [β
](https://huggingface.co/OpenDILabCommunity/Pendulum-v1-DDPG) | π | π | π | [β
](https://huggingface.co/OpenDILabCommunity/Hopper-v3-DDPG) | [β
](https://huggingface.co/OpenDILabCommunity/HalfCheetah-v3-DDPG) | [β
](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-DDPG) |
|
40 |
| [TD3](https://arxiv.org/pdf/1802.09477.pdf) | π | [β
](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-TD3) | [β
](https://huggingface.co/OpenDILabCommunity/BipedalWalker-v3-TD3) | [β
](https://huggingface.co/OpenDILabCommunity/Pendulum-v1-TD3) | π | π | π |[β
](https://huggingface.co/OpenDILabCommunity/Hopper-v3-TD3) | [β
](https://huggingface.co/OpenDILabCommunity/HalfCheetah-v3-TD3) | [β
](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-TD3) |
|
41 |
| [SAC](https://arxiv.org/pdf/1801.01290.pdf) | π | [β
](https://huggingface.co/OpenDILabCommunity/LunarLander-v2-SAC) | [β
](https://huggingface.co/OpenDILabCommunity/BipedalWalker-v3-SAC) | [β
](https://huggingface.co/OpenDILabCommunity/Pendulum-v1-SAC) | π | π | π | [β
](https://huggingface.co/OpenDILabCommunity/Hopper-v3-SAC) | [β
](https://huggingface.co/OpenDILabCommunity/HalfCheetah-v3-SAC) | [β
](https://huggingface.co/OpenDILabCommunity/Walker2d-v3-SAC) |
|
42 |
+
| [IMPALA](https://arxiv.org/pdf/1802.01561.pdf) | | | | | | | | | | |
|
43 |
|
44 |
</details>
|
45 |
|