Reinforcement Learning on Platform
98.7ReturnMP-DQN
Evaluation Results
| Method | Links | |
|---|---|---|
| MP-DQNMonte-Carlo returns=true2019.12 | 98.7 | |
| Hybrid SACMonte-Carlo returns=false2019.12 | 98.1 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| MP-DQNMonte-Carlo returns=true2019.12 | 98.7 | |
| Hybrid SACMonte-Carlo returns=false2019.12 | 98.1 |