Local Search for Policy Iteration in Continuous Control.
Jost Tobias SpringenbergNicolas HeessDaniel J. MankowitzJosh MerelArunkumar ByravanAbbas AbdolmalekiJackie KayJonas DegraveJulian SchrittwieserYuval TassaJonas BuchliDan BelovMartin A. RiedmillerPublished in: CoRR (2020)
Keyphrases
- policy iteration
- markov decision processes
- model free
- control system
- fixed point
- genetic algorithm
- stochastic approximation
- optimal policy
- optimal control
- control strategy
- search algorithm
- simulated annealing
- sample path
- policy evaluation
- finite state
- reinforcement learning
- tabu search
- least squares
- infinite horizon
- probabilistic model
- temporal difference
- control problems
- dynamic programming
- evolutionary algorithm
- search space