Inverse Policy Evaluation for Value-based Sequential Decision-making.
Alan ChanKristopher De AsisRichard S. SuttonPublished in: CoRR (2020)
Keyphrases
- sequential decision making
- policy evaluation
- temporal difference
- reinforcement learning
- matrix inversion
- function approximation
- model free
- monte carlo
- evaluation function
- policy iteration
- reinforcement learning algorithms
- state space
- action selection
- supervised learning
- markov decision processes
- least squares
- step size
- machine learning
- decision problems
- transfer learning
- dynamic programming
- lower bound
- learning algorithm