NBDI learns skill termination from state-action novelty (ICM prediction error) on task-agnostic demonstrations, improving downstream RL performance in maze and manipulation benchmarks.
Reinforcement Learning with NBDI In downstream learning, our objective is to learn a skill policy πθ(z|st) that maximizes the expected sum of discounted rewards, parameterized by θ
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations
NBDI learns skill termination from state-action novelty (ICM prediction error) on task-agnostic demonstrations, improving downstream RL performance in maze and manipulation benchmarks.