conftrace_

d4rl benchmark

7 papers

Explore in graph

Also known as

D4RL

Co-occurring keywords · papers mentioning both

offline reinforcement learning (5) value iteration (2) value function (2) deep reinforcement learning (2) expected-max q-learning (1) q-learning operator (1) behavioral policy (1) state-action pair (1) offline data (1) count-based conservatism (1)

Papers

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation ICML 2025 Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data ICML 2025 CORL: Research-oriented Deep Offline Reinforcement Learning Library NeurIPS 2023 Model-based Offline Reinforcement Learning with Count-based Conservatism ICML 2023 Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories ICML 2023 EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL ICML 2021 You Only Evaluate Once: a Simple Baseline Algorithm for Offline RL CoRL 2021