Stratified Experience Replay: Correcting Multiplicity Bias in Off-Policy Reinforcement Learning.
Brett DaleyCameron HickertChristopher AmatoPublished in: AAMAS (2021)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- state space
- robotic control
- information systems
- learning algorithm
- learning problems
- model free
- multi agent reinforcement learning
- decision making
- artificial neural networks
- user interface
- dynamic programming
- machine learning
- optimal policy
- genetic algorithm
- optimal control
- personal experiences
- information retrieval