Local Policy Optimization for Trajectory-Centric Reinforcement Learning.
Patrik KolaricDevesh K. JhaArvind U. RaghunathanFrank L. LewisMouhacine BenosmanDiego RomeresDaniel NikovskiPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- state space
- reinforcement learning problems
- reinforcement learning algorithms
- function approximation
- machine learning
- optimization problems
- optimization algorithm
- global optimization
- policy iteration
- partially observable environments
- markov decision process
- function approximators
- partially observable
- markov decision problems
- optimization process
- sufficient conditions
- control policy
- policy gradient
- model free
- approximate dynamic programming
- partially observable domains
- action space
- reward function
- optimization method
- markov decision processes
- least squares
- learning process
- multi agent
- learning algorithm