Distributed Policy Iteration for Scalable Approximation of Cooperative Multi-Agent Policies.
Thomy PhanKyrill SchmidLenz BelznerThomas GaborSebastian FeldClaudia Linnhoff-PopienPublished in: AAMAS (2019)
Keyphrases
- policy iteration
- optimal policy
- policy iteration algorithm
- markov decision processes
- linear approximation
- markov decision process
- cooperative multi agent
- reinforcement learning
- finite state
- policy evaluation
- approximate policy iteration
- markov decision problems
- infinite horizon
- discounted reward
- model free
- sample path
- fixed point
- temporal difference
- least squares
- optimal control
- state space
- average cost
- average reward
- approximate value iteration
- long run
- function approximation
- dynamic programming
- partially observable markov decision processes
- machine learning
- convergence rate
- multistage
- linear programming
- multi agent
- knowledge base
- learning algorithm