How to Choose the Optimal Policy in Multi-agent Belief Revision?
Yang GaoZhaochun SunNing LiPublished in: RSFDGrC (2003)
Keyphrases
- optimal policy
- belief revision
- multi agent
- reinforcement learning
- markov decision processes
- belief change
- decision problems
- state space
- propositional logic
- finite horizon
- state dependent
- dynamic programming
- long run
- logical properties
- multistage
- infinite horizon
- finite state
- minimal change
- belief update
- multi agent systems
- plausible inference
- markov decision process
- sufficient conditions
- knowledge base
- partially observable markov decision processes
- belief merging
- single agent
- initial state
- average cost
- average reward
- planning under uncertainty
- reward function
- multiple agents
- lost sales
- decision making
- machine learning