Distributed asynchronous policy iteration in dynamic programming.
Dimitri P. BertsekasHuizhen YuPublished in: Allerton (2010)
Keyphrases
- policy iteration
- dynamic programming
- markov decision processes
- optimal policy
- infinite horizon
- markov decision problems
- reinforcement learning
- model free
- approximate dynamic programming
- state space
- linear programming
- markov decision process
- fixed point
- optimal control
- sample path
- average reward
- finite state
- least squares
- multi agent
- temporal difference
- multistage
- partially observable
- policy evaluation
- average cost
- linear program
- pairwise