Reinforcement Learning on CartPole v0
200Mean ScoreCBRL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CBRLEpisode Number=1502024.06 | 200 | 0 | |
| CBRLEpisode Number=2002024.06 | 200 | 0 | |
| CBRLEpisode Number=2502024.06 | 200 | 0 | |
| CBRLEpisode Number=3002024.06 | 200 | 0 | |
| CBRLEpisode Number=3502024.06 | 200 | 0 | |
| CBRLEpisode Number=4002024.06 | 200 | 0 | |
| CBRLEpisode Number=4502024.06 | 200 | 0 | |
| CBRLEpisode Number=5002024.06 | 200 | 0 | |
| CBRLEpisode Number=1002024.06 | 199.69 | 0.63 | |
| XLVIN-RNumber of Trajectories=102021.10 | 199.2 | — | |
| XLVIN-CPNumber of Trajectories=102021.10 | 195.2 | — | |
| LinearEpisode Number=5002024.06 | 187.7 | 23.72 | |
| PPOEpisode Number=5002024.06 | 186.16 | 22.05 | |
| PPOEpisode Number=4502024.06 | 183.12 | 10.49 | |
| PRAE, J = 5Number of Trajectories=1002021.10 | 171.53 | — | |
| LinearEpisode Number=4502024.06 | 165.75 | 45.35 | |
| CBRLEpisode Number=502024.06 | 163.49 | 30.57 | |
| LD-AENumber of Trajectories=1002021.10 | 154.73 | — | |
| DQNEpisode Number=5002024.06 | 154.46 | 24.42 | |
| PPOEpisode Number=4002024.06 | 147.52 | 66.2 | |
| LinearEpisode Number=4002024.06 | 138.79 | 57.88 | |
| PPOEpisode Number=3502024.06 | 127.67 | 71.26 | |
| DQNEpisode Number=4502024.06 | 123.49 | 20.59 | |
| LinearEpisode Number=3502024.06 | 118.56 | 66.73 | |
| WM-AENumber of Trajectories=1002021.10 | 114.47 | — | |
| LinearEpisode Number=3002024.06 | 107.18 | 67.03 | |
| PPONumber of Trajectories=102021.10 | 104.6 | — | |
| PPOEpisode Number=3002024.06 | 102.31 | 57.89 | |
| DQNEpisode Number=4002024.06 | 80.85 | 31.94 | |
| LinearEpisode Number=2502024.06 | 80.05 | 56.27 | |
| PPOEpisode Number=2502024.06 | 75.65 | 50.67 | |
| DMDP-H (J = 0)Number of Trajectories=1002021.10 | 72.81 | — | |
| PPOEpisode Number=1502024.06 | 57.84 | 43.68 | |
| DQNEpisode Number=3502024.06 | 56.44 | 31.43 | |
| PPOEpisode Number=2002024.06 | 53.58 | 32.06 | |
| LinearEpisode Number=2002024.06 | 50.77 | 26.93 | |
| PPOEpisode Number=1002024.06 | 49.3 | 22.28 | |
| LinearEpisode Number=1502024.06 | 37.2 | 14.8 | |
| DQNEpisode Number=3002024.06 | 32.59 | 21.07 | |
| LinearEpisode Number=502024.06 | 27.15 | 7.79 | |
| LinearEpisode Number=1002024.06 | 27.05 | 7.21 | |
| PPOEpisode Number=502024.06 | 26.19 | 15.18 | |
| REINFORCENumber of Trajectories=1002021.10 | 23.84 | — | |
| DQNEpisode Number=502024.06 | 19.99 | 0.67 | |
| DQNEpisode Number=1002024.06 | 19.76 | 1.08 | |
| DQNEpisode Number=2002024.06 | 19.47 | 1.79 | |
| DQNEpisode Number=2502024.06 | 18.88 | 3.35 | |
| DQNEpisode Number=1502024.06 | 18.85 | 1.23 |