Softened Approximate Policy Iteration for Markov Games.
Julien PérolatBilal PiotMatthieu GeistBruno ScherrerOlivier PietquinPublished in: ICML (2016)
Keyphrases
- markov games
- approximate policy iteration
- markov decision processes
- multiagent reinforcement learning
- reinforcement learning algorithms
- markov decision process
- reinforcement learning
- control problems
- state space
- multiagent systems
- nash equilibrium
- cooperative
- optimal policy
- policy iteration
- multi agent
- finite state
- model free
- optimal stopping
- infinite horizon
- stochastic games
- temporal difference
- optimal control
- finite horizon
- dynamic programming
- learning algorithm
- reward function
- machine learning
- decision theoretic
- action space
- temporal difference learning
- function approximation
- generative model