REVIEW 2 cited by
Demonstration-Guided Reinforcement Learning with Learned Skills
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new task as an independent learning problem and attempt to follow the provided demonstrations step-by-step, akin to a human trying to imitate a completely unseen behavior by following the demonstrator's exact muscle movements. Naturally, such learning will be slow, but often new behaviors are not completely unseen: they share subtasks with behaviors we have previously learned. In this work, we aim to exploit this shared subtask structure to increase the efficiency of demonstration-guided RL. We first learn a set of reusable skills from large offline datasets of prior experience collected across many tasks. We then propose Skill-based Learning with Demonstrations (SkiLD), an algorithm for demonstration-guided RL that efficiently leverages the provided demonstrations by following the demonstrated skills instead of the primitive actions, resulting in substantial performance improvements over prior demonstration-guided RL approaches. We validate the effectiveness of our approach on long-horizon maze navigation and complex robot manipulation tasks.
Forward citations
Cited by 2 Pith papers
-
Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
ExRAP couples LLM planning with a temporal knowledge-graph memory and information-based exploration, improving success and efficiency for continual embodied instruction following.
-
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.
Discussion (0). Continue with ORCID to comment.