V-D-4RL

The 'V-D4RL' dataset/benchmark is a collection of pre-collected datasets used to evaluate the performance of offline reinforcement learning algorithms in various complex environments.

Papers using V-D-4RL (4)

MOORL: A Framework for Integrating Offline-Online Reinforcement Learning2025Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning2025Behavior Preference Regression for Offline Reinforcement Learning2025Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning2024