Multiagent Reinforcement Learning: Rollout and Policy Iteration.
Dimitri P. BertsekasPublished in: IEEE CAA J. Autom. Sinica (2021)
Keyphrases
- approximate policy iteration
- multiagent reinforcement learning
- markov games
- policy iteration
- markov decision processes
- stochastic games
- multiagent systems
- cooperative
- multi agent
- reinforcement learning algorithms
- markov decision process
- average reward
- reinforcement learning
- model free
- control problems
- temporal difference
- state space
- fixed point
- finite state
- multi robot
- nash equilibrium
- linear programming
- markov decision problems
- worst case
- average cost
- nash equilibria
- optimal policy