conftrace_

off-policy correction

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

distribution shift (2) distributed deep reinforcement learning (1) actor-learner architecture (1) importance weighted (1) interactive recommendation (1) natural language feedback (1) gpu parallelization (1) conservative q-function (1) breadth-first search (1) recommender system (1)

Papers

Text-Based Interactive Recommendation via Offline Reinforcement Learning AAAI 2022 Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction NeurIPS 2021 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures ICML 2018