Minimizing Return Gaps with Discrete Communications in Decentralized POMDP.
Jingdi ChenTian LanPublished in: CoRR (2023)
Keyphrases
- dec pomdps
- continuous state
- multi agent
- partially observable markov decision processes
- finite state
- dynamic programming
- reinforcement learning
- belief state
- dynamical systems
- infinite horizon
- continuous state spaces
- communication networks
- decision theoretic
- discrete version
- continuous action
- cooperative
- markov decision processes
- peer to peer
- state space
- model free reinforcement learning
- theoretical justification
- control policies
- discrete space
- single agent
- robot navigation
- continuous variables
- communication systems
- optimal policy
- distributed systems
- search algorithm