Reinforcement Learning on AdroitHandRelocate v1
30Average ReturnCausal PBRS
Evaluation results
| Method | Links | |
|---|---|---|
| Causal PBRSState Dim Removed=362026.02 | 30 | |
| T-REXState Dim Removed=362026.02 | 29 | |
| TrexState Dim Removed=362026.02 | 27 | |
| SAC BaselineState Dim Removed=362026.02 | 24 | |
| Recurrent SACState Dim Removed=362026.02 | 23 | |
| Causal PBRSState Dim Removed=362026.02 | 18 | |
| BaselineState Dim Removed=362026.02 | 17 | |
| Recurrent SACState Dim Removed=362026.02 | 17 | |
| CQLState Dim Removed=362026.02 | 13 | |
| CQLState Dim Removed=362026.02 | 13 |