Discovering Blind Spots in Reinforcement Learning.
Ramya RamakrishnanEce KamarDebadeepta DeyJulie A. ShahEric HorvitzPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- model free
- markov decision processes
- machine learning
- control problems
- learning algorithm
- direct policy search
- temporal difference
- learning process
- information systems
- optimal policy
- evolutionary algorithm
- case study
- decision trees
- decision making
- temporal difference learning
- reinforcement learning methods