← all datasets

Stochastic-D-4RL

Emerging
1papers using it
2025first seen

The 'Stochastic-D-4RL' dataset/benchmark is used to evaluate offline reinforcement learning algorithms in safety-critical domains by providing a set of stochastic decision-making tasks that require risk-aware policy learning.

🔎 Find this dataset

Papers using Stochastic-D-4RL (1)

Stochastic-D-4RL — datasets — reinforcement-learning