Value-aware Importance Weighting for Off-policy Reinforcement Learning.
Kristopher De AsisEric GravesRichard S. SuttonPublished in: CoLLAs (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- reinforcement learning algorithms
- machine learning
- supervised learning
- markov decision processes
- temporal difference
- databases
- similarity measure
- social networks
- learning process
- dynamic programming
- artificial intelligence
- learning algorithm
- weighting scheme
- term weighting