A Unifying View of Optimism in Episodic Reinforcement Learning.
Gergely NeuCiara Pike-BurkePublished in: NeurIPS (2020)
Keyphrases
- reinforcement learning
- learning algorithm
- state space
- robotic control
- reinforcement learning algorithms
- function approximation
- control problems
- optimal policy
- machine learning
- multi agent reinforcement learning
- temporal difference
- action selection
- model free
- artificial intelligence
- markov decision processes
- supervised learning
- optimal control
- dynamic programming
- learning process
- case study
- e learning
- decision making
- temporal difference learning
- episodic memory
- transition model
- relational reinforcement learning
- databases