conftrace_

behavior policy

30 papers

Explore in graph

Co-occurring keywords

offline reinforcement learning (492) off-policy evaluation (144) policy learning (702) policy constraint (16) support constraint (5) policy improvement (67) mean squared error (69) distribution shift (722) policy optimization (657) extrapolation error (9)

Papers

Offline RL Without Off-Policy Evaluation NIPS 2021
EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL ICML 2021
BRPO: Batch Residual Policy Optimization IJCAI 2020
Importance Sampling Policy Evaluation with an Estimated Behavior Policy ICML 2019
Data-Efficient Policy Evaluation Through Behavior Policy Search ICML 2017