Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313679546> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4313679546 abstract "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." @default.
- W4313679546 created "2023-01-08" @default.
- W4313679546 creator A5012754773 @default.
- W4313679546 creator A5014791481 @default.
- W4313679546 creator A5035420035 @default.
- W4313679546 creator A5049440980 @default.
- W4313679546 creator A5060255128 @default.
- W4313679546 date "2023-01-05" @default.
- W4313679546 modified "2023-09-26" @default.
- W4313679546 title "Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping" @default.
- W4313679546 doi "https://doi.org/10.48550/arxiv.2301.02099" @default.
- W4313679546 hasPublicationYear "2023" @default.
- W4313679546 type Work @default.
- W4313679546 citedByCount "0" @default.
- W4313679546 crossrefType "posted-content" @default.
- W4313679546 hasAuthorship W4313679546A5012754773 @default.
- W4313679546 hasAuthorship W4313679546A5014791481 @default.
- W4313679546 hasAuthorship W4313679546A5035420035 @default.
- W4313679546 hasAuthorship W4313679546A5049440980 @default.
- W4313679546 hasAuthorship W4313679546A5060255128 @default.
- W4313679546 hasBestOaLocation W43136795461 @default.
- W4313679546 hasConcept C10347200 @default.
- W4313679546 hasConcept C119857082 @default.
- W4313679546 hasConcept C136764020 @default.
- W4313679546 hasConcept C14036430 @default.
- W4313679546 hasConcept C154945302 @default.
- W4313679546 hasConcept C15744967 @default.
- W4313679546 hasConcept C180747234 @default.
- W4313679546 hasConcept C2780490138 @default.
- W4313679546 hasConcept C2986087404 @default.
- W4313679546 hasConcept C34413123 @default.
- W4313679546 hasConcept C41008148 @default.
- W4313679546 hasConcept C78458016 @default.
- W4313679546 hasConcept C86803240 @default.
- W4313679546 hasConcept C90509273 @default.
- W4313679546 hasConcept C97541855 @default.
- W4313679546 hasConceptScore W4313679546C10347200 @default.
- W4313679546 hasConceptScore W4313679546C119857082 @default.
- W4313679546 hasConceptScore W4313679546C136764020 @default.
- W4313679546 hasConceptScore W4313679546C14036430 @default.
- W4313679546 hasConceptScore W4313679546C154945302 @default.
- W4313679546 hasConceptScore W4313679546C15744967 @default.
- W4313679546 hasConceptScore W4313679546C180747234 @default.
- W4313679546 hasConceptScore W4313679546C2780490138 @default.
- W4313679546 hasConceptScore W4313679546C2986087404 @default.
- W4313679546 hasConceptScore W4313679546C34413123 @default.
- W4313679546 hasConceptScore W4313679546C41008148 @default.
- W4313679546 hasConceptScore W4313679546C78458016 @default.
- W4313679546 hasConceptScore W4313679546C86803240 @default.
- W4313679546 hasConceptScore W4313679546C90509273 @default.
- W4313679546 hasConceptScore W4313679546C97541855 @default.
- W4313679546 hasLocation W43136795461 @default.
- W4313679546 hasLocation W43136795462 @default.
- W4313679546 hasOpenAccess W4313679546 @default.
- W4313679546 hasPrimaryLocation W43136795461 @default.
- W4313679546 hasRelatedWork W2907045084 @default.
- W4313679546 hasRelatedWork W3022038857 @default.
- W4313679546 hasRelatedWork W3034786558 @default.
- W4313679546 hasRelatedWork W3211352205 @default.
- W4313679546 hasRelatedWork W4283694278 @default.
- W4313679546 hasRelatedWork W4286850169 @default.
- W4313679546 hasRelatedWork W4288021619 @default.
- W4313679546 hasRelatedWork W4293872189 @default.
- W4313679546 hasRelatedWork W4307308173 @default.
- W4313679546 hasRelatedWork W4311991951 @default.
- W4313679546 isParatext "false" @default.
- W4313679546 isRetracted "false" @default.
- W4313679546 workType "article" @default.