Reinforcement Learning on MountainCar (Pure)
-44.6Avg Reward (gamma=0.01)
CQL
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2021.02 | -44.6 | -500 | -499.3 | |
2021.02 | -44.6 | -500 | -500 | |
2021.02 | -44.7 | -500 | -500 | |
2021.02 | -44.7 | -500 | -490.1 | |
2021.02 | -44.7 | -500 | -492.1 | |
2021.02 | -44.79 | -380.7 | -500 | |
2021.02 | -46 | -500 | -500 | |
2021.02 | -50.01 | -373.6 | -352 | |
2021.02 | -53.95 | -182.9 | -197.5 | |
2021.02 | -53.95 | -182.9 | -197.5 | |
2021.02 | -53.95 | -182.9 | -197.5 | |
2021.02 | -54.2 | -191.2 | -199.7 | |
2021.02 | -54.6 | -189.7 | -200.3 | |
2021.02 | -55.23 | -481.7 | -496.2 | |
2021.02 | -56.73 | -463.2 | -478.9 | |
2021.02 | -56.8 | -189.4 | -210.6 | |
2021.02 | -61.3 | -373.2 | -428.5 | |
2021.02 | -61.4 | -366.9 | -429.1 | |
2021.02 | -67.6 | -267.8 | -295.1 | |
2021.02 | -71.21 | -286.6 | -328.3 | |
2021.02 | -74.23 | -492.3 | -500 | |
2021.02 | -79.4 | -357.9 | -407.6 | |
2021.02 | -83.5 | -357 | -407.4 | |
2021.02 | -94.87 | -358.7 | -486.5 | |
2021.02 | -102.3 | -500 | -500 | |
2021.02 | -106.3 | -432.3 | -471.8 | |
2021.02 | -107.6 | -500 | -500 | |
2021.02 | -176.1 | -316.4 | -362.9 | |
2021.02 | -364.5 | -260.6 | -204.5 | |
2021.02 | -373 | -500 | -500 |