TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations.
Junik BaeKwanyoung ParkYoungwoon LeePublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- supervised learning
- temporal information
- unsupervised learning
- temporal constraints
- spatio temporal
- semi supervised
- distance measure
- symbolic representation
- distance function
- reinforcement learning algorithms
- temporal data
- space time
- optimal policy
- temporal dimension
- deep belief networks
- learning classifier systems
- temporal relations
- neural network
- markov decision processes
- distance metric
- higher level
- nearest neighbor
- similarity measure
- machine learning