Reinforcement Learning on Goal
78.9P(Goal)MP-DQN
Evaluation results
| Method | Links | |
|---|---|---|
| MP-DQNMonte-Carlo returns=true2019.12 | 78.9 | |
| Hybrid SACMonte-Carlo returns=false2019.12 | 72.8 |
| Method | Links | |
|---|---|---|
| MP-DQNMonte-Carlo returns=true2019.12 | 78.9 | |
| Hybrid SACMonte-Carlo returns=false2019.12 | 72.8 |