Generation of Policy-Level Explanations for Reinforcement Learning.
Nicholay TopinManuela VelosoPublished in: AAAI (2019)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- markov decision process
- dynamic programming
- partially observable environments
- least squares
- function approximation
- reward function
- approximate dynamic programming
- policy gradient methods
- machine learning
- continuous state spaces
- policy evaluation
- state action
- control policy
- partially observable markov decision processes
- control problems
- state space
- multi agent