Reinforcement Learning on MuJoCo v4 (test)
5,244Avg Return (Ant-v4)BNTT
Evaluation results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| BNTTAlgorithm=TD3, Neuron Model=LIF, Random Seeds=52025.09 | 5,244 | 9,339 | 3,593 | — | — | — | — | — | 3,480 | 9,348 | 1.22 | — | — | |
| CaRe-BNAlgorithm=TD3, Neuron Model=LIF, Random Seeds=52025.09 | 5,083 | 8,813 | 3,489 | — | — | — | — | — | 4,556 | 9,346 | 3.92 | — | — | |
| tdBNAlgorithm=TD3, Neuron Model=LIF, Random Seeds=52025.09 | 4,876 | 8,845 | 3,601 | — | — | — | — | — | 4,098 | 9,346 | 1.65 | — | — | |
| ANN (TD3)Algorithm=TD3, Neuron Model=ANN Baseline, Random Seeds=52025.09 | 4,770 | 10,857 | 3,410 | — | — | — | — | — | 4,340 | 7,503 | 0 | — | — | |
| TABNAlgorithm=TD3, Neuron Model=LIF, Random Seeds=52025.09 | 4,431 | 9,173 | 3,474 | — | — | — | — | — | 3,818 | 9,347 | 1.64 | — | — | |
| TEBNAlgorithm=TD3, Neuron Model=LIF, Random Seeds=52025.09 | 4,408 | 9,452 | 3,472 | — | — | — | — | — | 4,235 | 9,347 | 0.69 | — | — | |
| Vanilla LIFAlgorithm=TD3, Neuron Model=LIF, Random Seeds=52025.09 | 4,243 | 9,073 | 3,507 | — | — | — | — | — | 2,807 | 9,347 | 7.08 | — | — | |
| WSRComparison=PPO vs. DDPG, Maximum trials (N)=10002026.03 | 27 | 8 | 13 | 42 | — | — | — | — | 23 | 677 | — | 89 | 1,758 | |
| N-SCORE∞Comparison=PPO vs. DDPG, Maximum trials (N)=10002026.03 | 21 | 8 | 12 | 40 | — | — | — | — | 22 | 267 | — | 77 | 894 | |
| WSRComparison=SAC vs. TD3, Maximum trials (N)=10002026.03 | 14 | 18 | 30 | 96 | — | — | — | — | 24 | — | — | 249 | 2,862 | |
| N-SCORE∞Comparison=SAC vs. TD3, Maximum trials (N)=10002026.03 | 13 | 15 | 20 | 89 | — | — | — | — | 22 | — | — | 220 | 2,758 |