Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.
Offline reinforcement learning with implicit Q-learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3representative citing papers
Delightful Policy Gradient gates updates with advantage times surprisal to suppress rare failures while preserving rare successes in distributed RL with stale or buggy data.
Weighted BC estimates trajectory density ratios from a clean reference set via binary discrimination and reweights the BC loss to converge to the clean expert policy with finite-sample bounds independent of contamination rate.
citing papers explorer
-
Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning
Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.
-
Delightful Distributed Policy Gradient
Delightful Policy Gradient gates updates with advantage times surprisal to suppress rare failures while preserving rare successes in distributed RL with stale or buggy data.
-
Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets
Weighted BC estimates trajectory density ratios from a clean reference set via binary discrimination and reweights the BC loss to converge to the clean expert policy with finite-sample bounds independent of contamination rate.