Jan 5, 2023 · In this work, we propose a novel self-supervised learning phase on the pre-collected dataset to understand the structure and the dynamics of the ...

In this work, we present a self-supervised reward shaping method that enables building an offline dataset with dense rewards. To this end, we develop a self ...

This is the original implementation of the paper. Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping [Project Page] [Paper].

Relabel transition with goal g and reward rt, and. Push (st ... We first list the hyper-parameters for the self-supervised reward shaping phase in Table 1.

Learning Goal-Conditioned Policies Offline with. Self-Supervised Reward Shaping. Rebuttal Document. Anonymous Author(s). Affiliation. Address email. 1 ...

These methods suffer from the issue of sparsity of rewards, and fail at long-horizon tasks. In this work, we propose a novel self-supervised learning phase on ...

Semantic Scholar extracted view of "Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping - Supplementary Material" by Lina ...

This paper proposes a novel magnetic field-based reward shaping (MFRS) method for goal-conditioned RL tasks with dynamic target and obstacles. Inspired by the ...

Jan 5, 2023 · These methods suffer from the issue of sparsity of rewards, and fail at long-horizon tasks. In this work, we propose a novel self-supervised ...