SRCP improves zero-shot generalization of successor representation methods in visual unsupervised reinforcement learning via saliency-guided representations and consistency policies.
Taco: temporal latent action-driven contrastive loss for visual re- inforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning
SRCP improves zero-shot generalization of successor representation methods in visual unsupervised reinforcement learning via saliency-guided representations and consistency policies.