A comprehensive benchmark study of offline imitation learning methods on multi-stage robot manipulation tasks identifies key sensitivities to algorithm design, data quality, and stopping criteria while releasing all datasets and code.
Emaq: Expected-max q-learning operator for simple yet effective offline and online RL.CoRR, abs/2007.11091
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Introduces relativised options and hierarchical abstraction to reuse experience across similar contexts in offline GCRL, with two algorithms demonstrating performance gains.
citing papers explorer
-
What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
A comprehensive benchmark study of offline imitation learning methods on multi-stage robot manipulation tasks identifies key sensitivities to algorithm design, data quality, and stopping criteria while releasing all datasets and code.
-
Abstraction for Offline Goal-Conditioned Reinforcement Learning
Introduces relativised options and hierarchical abstraction to reuse experience across similar contexts in offline GCRL, with two algorithms demonstrating performance gains.