Monte-Carlo Search for an Equilibrium in Dec-POMDPs.
Yang YouVincent ThomasFrancis ColasOlivier BuffetPublished in: UAI (2023)
Keyphrases
- dec pomdps
- monte carlo search
- evaluation function
- dynamic programming
- infinite horizon
- decision theoretic
- multi agent
- theoretical justification
- single agent
- continuous state
- monte carlo tree search
- nash equilibrium
- game theory
- planning under uncertainty
- optimal plans
- efficient computation
- decision making under uncertainty
- partially observable markov decision processes
- reinforcement learning
- markov decision problems
- optimal policy
- partially observable
- multiple agents
- monte carlo
- nash equilibria
- markov decision processes
- search algorithm
- real valued