We have 4 of 42 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
By learning transferable rewards, inverse reinforcement learning (IRL) enables counterfactual evaluation of agents under modified environments. Such transfer places strict requirements on coverage since target environments affect agents'state occupancy. We propose a multi-task IRL method that pools data across multiple...
The introduction of isotonic Bellman calibration, a one-dimensional, model-agnostic post-processing method that reduces residual occupancy-balance violations while preserving the ranking information in any initial occupancy-ratio estimate, and establishes finite-sample calibration guarantees and a KL oracle inequality...
Under \(Q\)-function realizability and local regularity, it is established that soft control locally inherits the contraction of policy evaluation in a discounted-occupancy norm, and local contraction and finite-sample convergence with estimated ratios are established.
Combining occupancy-weighted FQE with fitted occupancy-ratio evaluation gives an end-to-end guarantee governed by the complexities and direct approximation errors of the value-function and occupancy-ratio classes, removing the need for Bellman completeness.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
