Learning Markov State Abstractions for Deep Reinforcement Learning.
Cameron AllenNeev ParikhOmer GottesmanGeorge KonidarisPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- state space
- learning systems
- state abstraction
- learning problems
- active learning
- markov chain
- online learning
- knowledge acquisition
- supervised learning
- dynamic programming
- partially observable
- neural network
- learning styles
- markov decision processes
- function approximation
- reinforcement learning methods
- hidden state
- high level
- eligibility traces