ProtoX: Explaining a Reinforcement Learning Agent via Prototyping.
Ronilo J. RagodosTong WangQihang LinXun ZhouPublished in: CoRR (2022)
Keyphrases
- learning agent
- reinforcement learning
- state space
- reinforcement learning algorithms
- learning algorithm
- learning capabilities
- function approximation
- model free
- multi agent
- learning process
- solving problems
- selective perception
- learning tasks
- optimal policy
- single agent
- markov decision processes
- reward function
- dynamic environments
- expert systems
- heuristic search
- temporal difference
- action selection
- neural network
- sufficient conditions
- markov chain
- cooperative
- machine learning