Explanations from Deep Reinforcement Learning Using Episodic Memories.
Sam BlakemanDenis MareschalPublished in: HLC (2022)
Keyphrases
- reinforcement learning
- temporal difference
- function approximation
- machine learning
- state space
- control problems
- model free
- learning algorithm
- reinforcement learning algorithms
- associative memory
- markov decision processes
- optimal policy
- multi agent
- robotic control
- optimal control
- real world
- generating explanations
- learning process
- data mining
- learning problems
- mobile robot
- dynamic programming
- hidden markov models
- active learning
- bayesian networks
- deep learning
- action space
- learning agents
- genetic algorithm
- content addressable