Nash ε-equilibria for stochastic games with total reward functions: an approach through Markov decision processes.
Francisco J. González-PadillaRaúl Montes-de-OcaPublished in: Kybernetika (2019)
Keyphrases
- stochastic games
- markov decision processes
- total reward
- average reward
- optimal policy
- reinforcement learning algorithms
- reinforcement learning
- policy iteration
- nash equilibria
- state space
- finite state
- dynamic programming
- infinite horizon
- average cost
- finite horizon
- decision problems
- markov decision process
- long run
- action space
- partially observable
- learning agent
- game theoretic
- stationary policies
- markov chain