Reinforcement Learning on POPGym Stateless Pendulum (Hard)
82.8MMERGRU
Evaluation results
| Method | Links | |
|---|---|---|
| GRUImplementation Source=Morad et al., Framework=RLLib2023.03 | 82.8 | |
| LMUImplementation Source=Morad et al., Framework=RLLib2023.03 | 80.6 | |
| IndRNNImplementation Source=Morad et al., Framework=RLLib2023.03 | 80.4 | |
| S5Implementation Source=StableBaselines3/CleanRL, Framework=JAX, Parameter Matching=Matched to GRU params2023.03 | 79 | |
| GRUImplementation Source=StableBaselines3/CleanRL, Framework=JAX2023.03 | 75 | |
| FARTImplementation Source=Morad et al., Framework=RLLib2023.03 | 69.8 | |
| MLPImplementation Source=Morad et al., Framework=RLLib2023.03 | 47.7 | |
| MLPImplementation Source=StableBaselines3/CleanRL, Framework=JAX2023.03 | 41 | |
| S4DImplementation Source=Morad et al., Framework=RLLib2023.03 | 30.3 |