Reinforcement Learning on Procgen BigFish 1.0 (train)
20.8Mean Train PerformancePB2-Rand
Evaluation results
| Method | Links | |
|---|---|---|
| PB2-RandNumber of Agents=4, Timesteps=25M, Hyperparameter Initialization=Random, Evaluation Trials=1002021.06 | 20.8 | |
| PB2-MultNumber of Agents=4, Timesteps=25M, Hyperparameter Initialization=Random, Evaluation Trials=1002021.06 | 18.2 | |
| PB2-MixNumber of Agents=4, Timesteps=25M, Hyperparameter Initialization=Random, Evaluation Trials=1002021.06 | 17.1 | |
| UCB-DrACNumber of Agents=1, Timesteps=25M, Hyperparameter Initialization=Optimized, Evaluation Trials=1002021.06 | 13.2 | |
| PBTNumber of Agents=4, Timesteps=25M, Hyperparameter Initialization=Random, Evaluation Trials=1002021.06 | 12 | |
| PPONumber of Agents=1, Timesteps=25M, Hyperparameter Initialization=Optimized, Evaluation Trials=1002021.06 | 8.9 |