Warm-Starting Networks for Sample-Efficient Continuous Adaptation to Parameter Perturbations in Multi-Agent Reinforcement Learning
Deep reinforcement learning (RL) methods have made significant advancements over recent years toward mastering challenging problems. Because many real-world systems involve multiple agents interacting with each other in a shared environment, one particularly active subfield of RL is multi-agent rein...
| Váldodahkki: | |
|---|---|
| Eará dahkkit: | |
| Materiálatiipa: | Oahppočájánas |
| Almmustuhtton: |
Massachusetts Institute of Technology
2022
|
| Liŋkkat: | https://hdl.handle.net/1721.1/143288 |