Reinforcement Learning on POPGym Noisy Stateless Pendulum Hard
0.657MMERGRU
Evaluation Results
| Method | Links | |
|---|---|---|
| GRUImplementation Source=Morad et al., Framework=RLLib2023.03 | 0.657 | |
| GRUImplementation Source=StableBaselines3/CleanRL, Framework=JAX2023.03 | 0.61 | |
| LMUImplementation Source=Morad et al., Framework=RLLib2023.03 | 0.563 | |
| FARTImplementation Source=Morad et al., Framework=RLLib2023.03 | 0.553 | |
| S5Implementation Source=StableBaselines3/CleanRL, Framework=JAX, Parameter Matching=Matched to GRU params2023.03 | 0.55 | |
| IndRNNImplementation Source=Morad et al., Framework=RLLib2023.03 | 0.521 | |
| MLPImplementation Source=Morad et al., Framework=RLLib2023.03 | 0.351 | |
| MLPImplementation Source=StableBaselines3/CleanRL, Framework=JAX2023.03 | 0.34 | |
| S4DImplementation Source=Morad et al., Framework=RLLib2023.03 | 0.289 |