REVIEW 6 cited by
An Algorithmic Perspective on Imitation Learning
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
read the original abstract
As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingly challenging and expensive. Often, it is easier for a teacher to demonstrate a desired behavior rather than attempt to manually engineer it. This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning. This work provides an introduction to imitation learning. It covers the underlying assumptions, approaches, and how they relate; the rich set of algorithms developed to tackle the problem; and advice on effective tools and implementation. We intend this paper to serve two audiences. First, we want to familiarize machine learning experts with the challenges of imitation learning, particularly those arising in robotics, and the interesting theoretical and practical distinctions between it and more familiar frameworks like statistical supervised learning theory and reinforcement learning. Second, we want to give roboticists and experts in applied artificial intelligence a broader appreciation for the frameworks and tools available for imitation learning.
Forward citations
Cited by 6 Pith papers
-
REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning
Using only the replay buffers from RL training of domain-expert LLMs, REGEN trains a multi-domain generalist via offline RL and matches online multi-teacher distillation accuracy at a fraction of the reported training cost.
-
Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism
A learned proxy Q-function that triggers expert help when agent and expert actions diverge reduces human takeover cost and improves imitation learning efficiency in simulated driving and navigation.
-
Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving
C-HAC combines human demonstrations and reward-based RL for driving, using distributional return estimates to decide when the agent should follow the human-guided policy versus its self-learned policy.
-
Imitation Learning via Focused Satisficing
MinSubFI directly minimizes subdominance, a margin-based measure of failing to be acceptable, and empirically reports higher demonstrator acceptability than prior imitation methods.
-
Imitation Learning-Based Path Generation for the Complex Assembly of Deformable Objects
A behavior-cloning policy trained on 100 virtual and 10 human-corrected paths generates a reference trajectory for a rubber belt insertion task.
-
Principles of Robot Autonomy
A comprehensive textbook framing autonomous robots through a See-Think-Act pipeline, with exercises and notebooks, but no new technical findings.
Discussion (0). Continue with ORCID to comment.