HSVI-based online minimax strategies for partially observable stochastic games with neural perception mechanisms
We consider a variant of continuous-state partially-observable stochastic games with neural perception mechanisms and an asymmetric information structure. One agent has partial information, with the observation function implemented as a neural network, while the other agent is assumed to have full k...
| Κύριοι συγγραφείς: | , , , , |
|---|---|
| Μορφή: | Conference item |
| Γλώσσα: | English |
| Έκδοση: |
Journal of Machine Learning Research
2024
|