TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning.
Ruijie ZhengXiyao WangYanchao SunShuang MaJieyu ZhaoHuazhe XuHal Daumé IIIFurong HuangPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- action selection
- spatio temporal
- action space
- state space
- temporal constraints
- sensory inputs
- temporal analysis
- visual features
- spatial and temporal
- function approximation
- partially observable domains
- latent variables
- temporal reasoning
- reward shaping
- temporal information
- markov decision processes
- temporal databases
- model free
- state action
- machine learning
- temporal data
- space time
- temporal patterns
- temporal difference
- low level
- learning process
- high level