@rusu24edward , if I switch to multi-agent setting, I have to change a lot of code in rest of my codebase that uses learned policy. I think I should first give a shot to exploration. Can you please look into my follow up question here Using different get_exploration_action method pre and post training ?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Different step space for different agents | 7 | 886 | August 11, 2021 | |
| Using different get_exploration_action logic pre and post training | 1 | 428 | November 11, 2022 | |
| Mutiagent - Different action space for different agents | 8 | 1904 | August 25, 2022 | |
| MultiAgents type actions/observation space defined in environement | 8 | 1452 | May 10, 2022 | |
| Multiple training phases with different configurations | 2 | 255 | January 7, 2023 |