A Unifying View of Optimism in Episodic Reinforcement Learning.
Gergely NeuCiara Pike-BurkePublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- optimal policy
- state space
- reinforcement learning algorithms
- model free
- learning algorithm
- markov decision processes
- robotic control
- learning problems
- machine learning
- multi agent
- website
- information systems
- optimal control
- robot control
- learning process
- data mining
- temporal difference
- real world
- markov decision process
- learning agents
- relational reinforcement learning
- neural network