Interference and Generalization in Temporal Difference Learning.
Emmanuel BengioJoelle PineauDoina PrecupPublished in: ICML (2020)
Keyphrases
- dynamic environments
- temporal difference learning
- reinforcement learning algorithms
- function approximation
- fixed point
- evaluation function
- reinforcement learning
- temporal difference
- approximate value iteration
- game playing
- markov decision process
- monte carlo
- policy iteration
- markov decision processes
- dynamical systems
- supervised learning
- state space
- active learning