Reinforcement Learning on LunarLanderContinuous v2
533.6Mean RewardLinear
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LinearEpisode Number=1002024.06 | 533.6 | 130.04 | |
| LinearEpisode Number=502024.06 | 531.05 | 115.63 | |
| LinearEpisode Number=2002024.06 | 513.44 | 129.48 | |
| LinearEpisode Number=1502024.06 | 510.13 | 123.56 | |
| LinearEpisode Number=5002024.06 | 492.67 | 126.01 | |
| LinearEpisode Number=3502024.06 | 479.01 | 124.67 | |
| LinearEpisode Number=2502024.06 | 475.43 | 125.81 | |
| LinearEpisode Number=3002024.06 | 473.77 | 127.78 | |
| LinearEpisode Number=4002024.06 | 458.1 | 131.61 | |
| LinearEpisode Number=4502024.06 | 445.52 | 143.65 | |
| PPOEpisode Number=502024.06 | 403.56 | 143.06 | |
| DDPGEpisode Number=502024.06 | 337.22 | 98.64 | |
| TTOptMode size (N)=32022.04 | 290.29 | 24.4 | |
| TTOptMode size (N)=2^82022.04 | 286.87 | 21.65 | |
| GAMode size (N)=32022.04 | 283.05 | 16.28 | |
| DTSemNetNf (Number of features)=8, Na (Number of actions)=2 dim., Height=4, Variant=Top-k2026.05 | 282.49 | — | |
| CBRLEpisode Number=2502024.06 | 280.36 | 17.19 | |
| CBRLEpisode Number=5002024.06 | 280.09 | 17.16 | |
| CBRLEpisode Number=3502024.06 | 280.08 | 17.14 | |
| CBRLEpisode Number=4002024.06 | 279.51 | 17.67 | |
| CBRLEpisode Number=2002024.06 | 279.24 | 18.12 | |
| CBRLEpisode Number=3002024.06 | 279.19 | 18.42 | |
| CBRLEpisode Number=4502024.06 | 278.96 | 19.22 | |
| DTSemNetNf (Number of features)=8, Na (Number of actions)=2 dim., Height=4, Variant=STE2026.05 | 277.24 | — | |
| Deep RLNf (Number of features)=8, Na (Number of actions)=2 dim., Height=42026.05 | 276.12 | — | |
| SAC2025.02 | 272.7 | — | |
| SALSA-RLLatent dimension size (hd)=42025.02 | 268.3 | — | |
| DGTNf (Number of features)=8, Na (Number of actions)=2 dim., Height=4, Variant=linear2026.05 | 267.9 | — | |
| SALSA-RLLatent dimension size (hd)=82025.02 | 260.8 | — | |
| PPOEpisode Number=1002024.06 | 260.08 | 238.84 | |
| CBRLEpisode Number=1502024.06 | 258.84 | 31.52 | |
| SALSA-RLLatent dimension size (hd)=32025.02 | 257.8 | — | |
| ICCTNf (Number of features)=8, Na (Number of actions)=2 dim., Height=42026.05 | 255.57 | — | |
| DSP2025.02 | 251.7 | — | |
| DDPG2025.02 | 246.2 | — | |
| SALSA-RLLatent dimension size (hd)=62025.02 | 246.1 | — | |
| SALSA-RLLatent dimension size (hd)=162025.02 | 242.6 | — | |
| A2C2025.02 | 227.1 | — | |
| TD32025.02 | 225.4 | — | |
| PPO2025.02 | 225.1 | — | |
| CMAESMode size (N)=2^82022.04 | 221.95 | 133.8 | |
| CMAESMode size (N)=32022.04 | 214.55 | 93.79 | |
| GAMode size (N)=2^82022.04 | 213.75 | 99.67 | |
| PPOEpisode Number=1502024.06 | 188.5 | 121.78 | |
| DDPGEpisode Number=1502024.06 | 154.48 | 43.2 | |
| DDPGEpisode Number=1002024.06 | 145.05 | 42.29 | |
| DDPGEpisode Number=2502024.06 | 143.46 | 112.2 | |
| DDPGEpisode Number=2002024.06 | 133.51 | 38.96 | |
| DDPGEpisode Number=5002024.06 | 133.2 | 66.54 | |
| DGTNf (Number of features)=8, Na (Number of actions)=2 dim., Height=4, Variant=scalar2026.05 | 131.92 | — | |
| CBRLEpisode Number=502024.06 | 128.81 | 276.58 | |
| PPOEpisode Number=2502024.06 | 127.29 | 81.82 | |
| OPENESMode size (N)=32022.04 | 114.97 | 113.48 | |
| PPOEpisode Number=3002024.06 | 109.72 | 79.65 | |
| PPOEpisode Number=2002024.06 | 106.87 | 133.97 | |
| CBRLEpisode Number=1002024.06 | 101.33 | 262.09 | |
| PPOEpisode Number=5002024.06 | 96.5 | 113.1 | |
| PPOEpisode Number=4502024.06 | 91.77 | 105.02 | |
| PPOEpisode Number=4002024.06 | 75.52 | 111.54 | |
| DDPGEpisode Number=3002024.06 | 73.1 | 70.24 | |
| OPENESMode size (N)=2^82022.04 | 73.08 | 163.33 | |
| DDPGEpisode Number=4002024.06 | 70.04 | 120.93 | |
| DDPGEpisode Number=4502024.06 | 51.15 | 99.21 | |
| PPOEpisode Number=3502024.06 | 45.12 | 140.02 | |
| DDPGEpisode Number=3502024.06 | 9.04 | 98.49 |