A Bayesian reinforcement learning approach in markov games for computing near-optimal policies.
Julio B. ClempnerPublished in: Ann. Math. Artif. Intell. (2023)
Keyphrases
- bayesian reinforcement learning
- optimal policy
- markov games
- markov decision processes
- reinforcement learning
- multiagent reinforcement learning
- markov decision process
- monte carlo tree search
- partially observable markov decision processes
- dynamic programming
- reinforcement learning algorithms
- finite state
- state space
- markov decision problems
- infinite horizon
- long run
- policy iteration
- sufficient conditions
- multi agent
- partially observable
- average cost
- function approximation
- decision problems
- average reward
- stochastic games
- monte carlo
- multiagent systems
- linear programming