Single Episode Policy Transfer in Reinforcement Learning.
Jiachen YangBrenden K. PetersenHongyuan ZhaDaniel FaissolPublished in: ICLR (2020)
Keyphrases
- reinforcement learning
- optimal policy
- transfer learning
- approximate dynamic programming
- markov decision processes
- action selection
- partially observable domains
- machine learning
- partially observable environments
- function approximators
- policy iteration
- markov decision process
- partially observable
- model free
- state space
- multi agent
- temporal difference
- optimal control
- average reward
- policy making
- policy gradient
- actor critic
- policy search
- reinforcement learning problems
- learning process