ORCA rewards an agent for covering all demonstration subgoal frames in order, and outperforms frame-level matching baselines on Meta-world and Humanoid-v4 benchmarks under temporal misalignment.
cc/paper_files/paper/2017/file/ ba3866600c3540f67c1e9575e213be0a-Paper
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
-
Imitation Learning from a Single Temporally Misaligned Video
ORCA rewards an agent for covering all demonstration subgoal frames in order, and outperforms frame-level matching baselines on Meta-world and Humanoid-v4 benchmarks under temporal misalignment.