NeoRL-2
Emerging3papers using it
2025first seen
The 'NeoRL-2' dataset/benchmark contains a variety of offline reinforcement learning tasks and is used to evaluate the performance of reinforcement learning algorithms, particularly in the context of policy constraints.
Papers using NeoRL-2 (3)
- Automatic Constraint Policy Optimization based on Continuous Constraint Interpolation Framework for Offline Reinforcement LearningQuantile Q-Learning: Revisiting Offline Extreme Q-Learning with Quantile RegressionPIQL: Projective Implicit Q-Learning with Support Constraint for Offline Reinforcement Learning