Population-Guided Parallel Policy Search for Reinforcement Learning.
Whiyoung JungGiseung ParkYoungchul SungPublished in: CoRR (2020)
Keyphrases
- policy search
- reinforcement learning
- reinforcement learning algorithms
- continuous state
- dynamic programming
- continuous action
- policy gradient
- learning algorithm
- reward function
- state space
- function approximation
- action selection
- markov decision processes
- learning problems
- evaluation function
- partially observable markov decision processes
- control policies
- monte carlo methods
- computational complexity