Invariant causal prediction for block MDPs
Generalization across environments is critical to the successful application of reinforcement learning (RL) algorithms to real-world challenges. In this work we propose a method for learning state abstractions which generalize to novel observation distributions in the multi-environment RL setting. W...
| Үндсэн зохиолчид: | , , , , , , , |
|---|---|
| Формат: | Conference item |
| Хэл сонгох: | English |
| Хэвлэсэн: |
Proceedings of Machine Learning Research
2020
|