← Back to all news
arXiv Machine Learning By Bryce MacInnis, Malcolm I. Heywood

Making Strides in Symbolic Imitation Learning: Offline Demonstrations, Online Tuning

Read the original on arXiv Machine Learning →

The paper introduces Symbolic Imitation Learning, a framework that distills an oracle policy from an offline dataset into a decision list using linear model motion primitives. By combining this with online Augmented‑Random Search tuning, the resulting interpretable policies match or surpass the oracle’s performance on 20 benchmark reinforcement learning tasks. The approach yields concise, understandable policies that domain experts can readily interpret.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Oct 12

Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies

The paper extends theoretical guarantees for offline reinforcement learning to parameterized policy classes over large or continuous action spaces, overcoming limitations of prior algorithms that required finite action sets and state‑wise mirror descent. By addressing contextual coupling and linking mirror descent to natural policy gradients, the authors provide new analyses, algorithmic insights, and a surprising connection between offline RL and imitation learning.

By Xiang Li, Yuheng Zhang, Nan Jiang
reinforcement-learning
More like this →
arXiv AI
Oct 1

SynIL: Leveraging Synergy for Offline Imitation Learning from Imperfect Demonstration Datasets

SynIL is a new framework for offline imitation learning that automatically assesses the quality of demonstration data without requiring labels. It uses motor synergy—a low‑dimensional coordinated movement pattern linked to proficiency—to generate dense, transition‑level reward signals through self‑supervised reward regression. Experiments on D4RL locomotion and Robomimic manipulation datasets show that synergy‑derived rewards align well with true rewards and that SynIL outperforms Behavior Cloning and rivals or surpasses offline reinforcement learning in sparse‑reward scenarios.

By Yuto Tanaka, Kyo Kutsuzawa, Martina Doku, Dai Owaki, Mitsuhiro Hayashibe
reinforcement-learningroboticsbenchmarks
More like this →