Blending Imitation and Reinforcement Learning for Robust Policy Improvement.
Xuefeng LiuTakuma YonedaRick L. StevensMatthew R. WalterYuxin ChenPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- partially observable environments
- approximate dynamic programming
- partially observable
- function approximation
- reinforcement learning algorithms
- decision problems
- state space
- function approximators
- partially observable domains
- policy gradient
- control policies
- control policy
- action space
- policy iteration
- model free
- partial occlusion
- computationally efficient
- computational models
- dynamical systems
- neural network
- markov decision problems
- markov decision processes
- markov chain
- actor critic
- reinforcement learning problems
- multi agent