QXplore: Q-learning Exploration by Maximizing Temporal Difference Error.
Riley Simmons-EdlerBen EisnerEric MitchellH. Sebastian SeungDaniel D. LeePublished in: CoRR (2019)
Keyphrases
- temporal difference
- action selection
- td learning
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- temporal difference learning
- model free
- temporal difference methods
- policy iteration
- evaluation function
- policy evaluation
- function approximators
- monte carlo
- reinforcement learning methods
- actor critic
- state space
- td methods
- step size
- decision making
- radial basis function
- supervised learning
- markov games
- neural network