(When) Are Contrastive Explanations of Reinforcement Learning Helpful?
Sanjana NarayananIsaac LageFinale Doshi-VelezPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- state space
- optimal policy
- model free
- reinforcement learning algorithms
- multi agent reinforcement learning
- learning algorithm
- machine learning
- optimal control
- dynamic programming
- temporal difference
- action selection
- learning capabilities
- control problems
- generating explanations
- learning problems
- learning classifier systems
- causal models
- transfer learning
- artificial neural networks
- multi agent
- case study
- genetic algorithm