TempoRL: Temporal Priors for Exploration in Off-Policy Reinforcement Learning.
Marco BagatellaSammy ChristenOtmar HilligesPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- active exploration
- temporal analysis
- state space
- spatio temporal
- action selection
- exploration exploitation
- exploration strategy
- function approximation
- reinforcement learning algorithms
- spatial and temporal
- temporal constraints
- temporal reasoning
- machine learning
- temporal consistency
- temporal data
- bayesian framework
- temporal information
- temporal difference
- model based reinforcement learning
- temporal databases
- optimal policy
- prior information
- model free
- temporal dimension
- supervised learning
- prior knowledge
- temporal abstractions
- learning algorithm
- genetic algorithm
- data sets