Reinforcement Learning on POPGym Repeat Previous Hard
91MMERS5
Evaluation Results
| Method | Links | |
|---|---|---|
| S5Implementation Source=StableBaselines3/CleanRL, Framework=JAX, Parameter Matching=Matched to GRU params2023.03 | 91 | |
| LMUImplementation Source=Morad et al., Framework=RLLib2023.03 | 19.1 | |
| IndRNNImplementation Source=Morad et al., Framework=RLLib2023.03 | -38.4 | |
| GRUImplementation Source=Morad et al., Framework=RLLib2023.03 | -42.8 | |
| GRUImplementation Source=StableBaselines3/CleanRL, Framework=JAX2023.03 | -46 | |
| MLPImplementation Source=StableBaselines3/CleanRL, Framework=JAX2023.03 | -48 | |
| FARTImplementation Source=Morad et al., Framework=RLLib2023.03 | -48.5 | |
| MLPImplementation Source=Morad et al., Framework=RLLib2023.03 | -48.6 | |
| S4DImplementation Source=Morad et al., Framework=RLLib2023.03 | -49.1 |