3 datasets found

The dataset used in the paper is the BabyAI environment 'BabyAI-PickUpDist-v0' with a one-pickup-per-episode wrapper.

Offline Goal-Conditioned Reinforcement Learning (Offline GCRL) is an important problem in RL that focuses on acquiring diverse goal-oriented skills solely from pre-collected...

The dataset used in the paper is a collection of trajectories for goal-conditioned reinforcement learning tasks.