single-file implementations of RL algorithms so i can actually do research
| Algorithm | Code | W&B |
|---|---|---|
| Actor-Critic | algos/pytorch/torch_actor_critic.py | |
| APS | algos/aps.py, algos/aps_minidoom.py | |
| CRL | algos/crl.py, algos/scaling_crl.py | |
| DQN | algos/pytorch/torch_cleanrl_dqn_atari.py | |
| PPO | algos/ppo.py, algos/pytorch/torch_cleanrl_ppo_atari.py | Brax |
| Rainbow | algos/pytorch/torch_cleanrl_rainbow_atari.py | |
| RCP | algos/rcp.py | |
| DIAYN | algos/diayn.py | |
| E3B | algos/e3b.py, algos/e3b_minidoom.py | |
| ICM | algos/icm.py, algos/icm_vizdoom.py | |
| Predictron | algos/pytorch/torch_predictron.py | |
| Recurrent Visual Attention | algos/pytorch/torch_recurrent_visual_attention.py | |
| REINFORCE | algos/pytorch/torch_reinforce.py | |
| RND | algos/rnd.py, algos/rnd_atari.py | Brax, Atari |
| SMiRL | algos/smirl.py | |
| SMM | algos/smm.py | |
| Squeeze-Excitation | algos/squeeze_excitation.py | |
| UDRL | algos/udrl.py | |
| VAE | algos/pytorch/torch_vae.py | |
| VQ-VAE | algos/pytorch/torch_vq_vae.py | |
| EBD | algos/ebd.py |
similar projects