Papers › Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping

Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping

5 Jan 2023arXiv:2301.02099archive 2025-07-28

Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski, Alessandro Lazaric, Karteek Alahari

Developing agents that can execute multiple skills by learning from pre-collected datasets is an important problem in robotics, where online interaction with the environment is extremely time-consuming. Moreover, manually designing reward functions for every single desired skill is prohibitive. Prior works targeted these challenges by learning goal-conditioned policies from offline datasets without manually specified rewards, through hindsight relabelling. 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 the pre-collected dataset to understand the structure and the dynamics of the model, and shape a dense reward function for learning policies offline. We evaluate our method on three continuous control tasks, and show that our model significantly outperforms existing approaches, especially on tasks that involve long-term planning.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

facebookresearch/go-fresh officialmentioned in paperpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Continuous ControlSelf-Supervised Learningcontinuous-control

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

fail

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections