Widest Paths and Global Propagation in Bounded Value Iteration for Stochastic Games.
Kittiphon PhalakarnToru TakisakaThomas HaasIchiro HasuoPublished in: CAV (2) (2020)
Keyphrases
- stochastic games
- markov decision processes
- average reward
- reinforcement learning algorithms
- infinite horizon
- multiagent reinforcement learning
- state space
- optimal policy
- reinforcement learning
- nash equilibria
- heuristic search
- long run
- finite state
- least squares
- policy iteration
- shortest path
- multi agent
- machine learning
- video games
- partially observable
- path finding
- robust optimization
- dynamic programming
- cooperative