Reinforcement Learning on LunarLander (Average Episode Reward)
283.56Average Episode RewardESPL
Evaluation Results
| Method | Links | |
|---|---|---|
| ESPL2023.11 | 283.56 | |
| SAC2023.11 | 276.92 | |
| TD32023.11 | 272.13 | |
| ACKTR2023.11 | 271.53 | |
| PPO2023.11 | 269.65 | |
| DDPG2023.11 | 266.05 | |
| TRPO2023.11 | 265.26 | |
| DSP2023.11 | 261.36 | |
| DTSemNetNf (Number of features)=8, Na (Number of actions)=4, Height=52026.05 | 252.5 | |
| Deep RLNf (Number of features)=8, Na (Number of actions)=4, Height=52026.05 | 245 | |
| A2C2023.11 | 238.51 | |
| DGTNf (Number of features)=8, Na (Number of actions)=4, Height=52026.05 | 183.6 | |
| VIPERNf (Number of features)=8, Na (Number of actions)=4, Height=52026.05 | 86.73 | |
| Regression2023.11 | 56.08 | |
| ICCTNf (Number of features)=8, Na (Number of actions)=4, Height=52026.05 | -85 |