Skip to content
conftrace_

reward extrapolation

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

inverse reinforcement learning (2) imitation learning (2) interactive recommendation (1) logged feedback (1) demonstration ranking (1) distribution mismatch (1) trajectory ranking (1) recommendation system (1) behavioral cloning (1) reward learning (1)

Papers

A General Offline Reinforcement Learning Framework for Interactive Recommendation AAAI 2021 Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations CoRL 2019 Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations ICML 2019