Feature-Based Q-Learning for Two-Player Stochastic Games.
Zeyu JiaLin F. YangMengdi WangPublished in: CoRR (2019)
Keyphrases
- stochastic games
- reinforcement learning algorithms
- multi agent reinforcement learning
- state action
- single agent
- reinforcement learning
- multi agent
- nash equilibria
- markov decision processes
- model free
- repeated games
- state space
- learning agent
- multiagent reinforcement learning
- function approximation
- temporal difference
- rl algorithms
- learning algorithm
- nash equilibrium
- multiple agents
- reward function
- imperfect information
- cooperative
- long run
- game theory
- optimal policy
- dynamic environments
- multi agent systems
- decision problems
- search algorithm
- average reward
- robust optimization
- fixed point
- game theoretic