VeoRL, which aligns real-action rollouts with latent-behavior rollouts learned from unlabeled videos, reports substantial improvements over offline visual RL baselines across three benchmarks.
Handle Press w/ MMD loss w/o MMD loss DreamerV2 Episode return 2651± 620 1961 ± 585 1202 ± 422 Success rate 0.60± 0.12 0.45 ± 0.15 0.33 ± 0.11 W/ MMD loss W/o MMD loss Figure
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach
VeoRL, which aligns real-action rollouts with latent-behavior rollouts learned from unlabeled videos, reports substantial improvements over offline visual RL baselines across three benchmarks.