Generation of Policy-Level Explanations for Reinforcement Learning.
Nicholay TopinManuela VelosoPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- optimal policy
- action selection
- policy search
- levels of abstraction
- markov decision processes
- partially observable
- partially observable environments
- machine learning
- actor critic
- approximate dynamic programming
- policy making
- control policies
- control problems
- reward function
- higher level
- state space
- dynamic programming
- learning environment
- multi agent
- decision making