conftrace_

value overestimation

6 papers

Explore in graph

Co-occurring keywords

offline reinforcement learning (492) conservative q-learning (13) extrapolation error (9) out-of-distribution action (9) in-sample learning (1) mild generalization (1) edge-of-reach problem (1) dynamics model (67) policy regularization (13) distributional shift (60)

Papers

Doubly Mild Generalization for Offline Reinforcement Learning NIPS 2024
The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning NIPS 2024
Policy Regularization with Dataset Constraint for Offline Reinforcement Learning ICML 2023
Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning NIPS 2023
Conservative Q-Learning for Offline Reinforcement Learning NIPS 2020
Double Q-learning NIPS 2010