Abstraction for Deep Reinforcement Learning.
Murray ShanahanMelanie MitchellPublished in: IJCAI (2022)
Keyphrases
- reinforcement learning
- state abstraction
- function approximation
- temporal abstractions
- high level
- markov decision processes
- reinforcement learning algorithms
- learning algorithm
- multi agent
- state space
- temporal difference
- direct policy search
- decision theoretic planning
- real time
- temporal difference learning
- model free
- learning problems
- action selection
- learning classifier systems
- information systems
- low level
- multi agent reinforcement learning
- dynamic programming
- robotic control
- supervised learning