Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225616484> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4225616484 abstract "In this work, we focus on multi-step manipulation tasks that involve long-horizon planning and considers progress reversal. Such tasks interlace high-level reasoning that consists of the expected states that can be attained to achieve an overall task and low-level reasoning that decides what actions will yield these states. We propose a sample efficient Previous Action Conditioned Robotic Manipulation Network (PAC-RoManNet) to learn the action-value functions and predict manipulation action candidates from visual observation of the scene and action-value predictions of the previous action. We define a Task Progress based Gaussian (TPG) reward function that computes the reward based on actions that lead to successful motion primitives and progress towards the overall task goal. To balance the ratio of exploration/exploitation, we introduce a Loss Adjusted Exploration (LAE) policy that determines actions from the action candidates according to the Boltzmann distribution of loss estimates. We demonstrate the effectiveness of our approach by training PAC-RoManNet to learn several challenging multi-step robotic manipulation tasks in both simulation and real-world. Experimental results show that our method outperforms the existing methods and achieves state-of-the-art performance in terms of success rate and action efficiency. The ablation studies show that TPG and LAE are especially beneficial for tasks like multiple block stacking. Additional experiments on Ravens-10 benchmark tasks suggest good generalizability of the proposed PAC-RoManNet." @default.
- W4225616484 created "2022-05-05" @default.
- W4225616484 creator A5009003218 @default.
- W4225616484 creator A5023942737 @default.
- W4225616484 creator A5031476331 @default.
- W4225616484 date "2022-02-22" @default.
- W4225616484 modified "2023-10-17" @default.
- W4225616484 title "Learning Multi-step Robotic Manipulation Policies from Visual Observation of Scene and Q-value Predictions of Previous Action" @default.
- W4225616484 doi "https://doi.org/10.48550/arxiv.2202.11280" @default.
- W4225616484 hasPublicationYear "2022" @default.
- W4225616484 type Work @default.
- W4225616484 citedByCount "0" @default.
- W4225616484 crossrefType "posted-content" @default.
- W4225616484 hasAuthorship W4225616484A5009003218 @default.
- W4225616484 hasAuthorship W4225616484A5023942737 @default.
- W4225616484 hasAuthorship W4225616484A5031476331 @default.
- W4225616484 hasBestOaLocation W42256164841 @default.
- W4225616484 hasConcept C105795698 @default.
- W4225616484 hasConcept C119857082 @default.
- W4225616484 hasConcept C121332964 @default.
- W4225616484 hasConcept C13280743 @default.
- W4225616484 hasConcept C14036430 @default.
- W4225616484 hasConcept C144024400 @default.
- W4225616484 hasConcept C154945302 @default.
- W4225616484 hasConcept C162324750 @default.
- W4225616484 hasConcept C185798385 @default.
- W4225616484 hasConcept C187736073 @default.
- W4225616484 hasConcept C189645446 @default.
- W4225616484 hasConcept C205649164 @default.
- W4225616484 hasConcept C2524010 @default.
- W4225616484 hasConcept C27158222 @default.
- W4225616484 hasConcept C2777210771 @default.
- W4225616484 hasConcept C2780451532 @default.
- W4225616484 hasConcept C2780791683 @default.
- W4225616484 hasConcept C33923547 @default.
- W4225616484 hasConcept C41008148 @default.
- W4225616484 hasConcept C46312422 @default.
- W4225616484 hasConcept C62520636 @default.
- W4225616484 hasConcept C78458016 @default.
- W4225616484 hasConcept C86803240 @default.
- W4225616484 hasConcept C97541855 @default.
- W4225616484 hasConceptScore W4225616484C105795698 @default.
- W4225616484 hasConceptScore W4225616484C119857082 @default.
- W4225616484 hasConceptScore W4225616484C121332964 @default.
- W4225616484 hasConceptScore W4225616484C13280743 @default.
- W4225616484 hasConceptScore W4225616484C14036430 @default.
- W4225616484 hasConceptScore W4225616484C144024400 @default.
- W4225616484 hasConceptScore W4225616484C154945302 @default.
- W4225616484 hasConceptScore W4225616484C162324750 @default.
- W4225616484 hasConceptScore W4225616484C185798385 @default.
- W4225616484 hasConceptScore W4225616484C187736073 @default.
- W4225616484 hasConceptScore W4225616484C189645446 @default.
- W4225616484 hasConceptScore W4225616484C205649164 @default.
- W4225616484 hasConceptScore W4225616484C2524010 @default.
- W4225616484 hasConceptScore W4225616484C27158222 @default.
- W4225616484 hasConceptScore W4225616484C2777210771 @default.
- W4225616484 hasConceptScore W4225616484C2780451532 @default.
- W4225616484 hasConceptScore W4225616484C2780791683 @default.
- W4225616484 hasConceptScore W4225616484C33923547 @default.
- W4225616484 hasConceptScore W4225616484C41008148 @default.
- W4225616484 hasConceptScore W4225616484C46312422 @default.
- W4225616484 hasConceptScore W4225616484C62520636 @default.
- W4225616484 hasConceptScore W4225616484C78458016 @default.
- W4225616484 hasConceptScore W4225616484C86803240 @default.
- W4225616484 hasConceptScore W4225616484C97541855 @default.
- W4225616484 hasLocation W42256164841 @default.
- W4225616484 hasOpenAccess W4225616484 @default.
- W4225616484 hasPrimaryLocation W42256164841 @default.
- W4225616484 hasRelatedWork W1992155208 @default.
- W4225616484 hasRelatedWork W2558486663 @default.
- W4225616484 hasRelatedWork W2568452623 @default.
- W4225616484 hasRelatedWork W2891191051 @default.
- W4225616484 hasRelatedWork W3132645524 @default.
- W4225616484 hasRelatedWork W3136007272 @default.
- W4225616484 hasRelatedWork W3166789302 @default.
- W4225616484 hasRelatedWork W3175415172 @default.
- W4225616484 hasRelatedWork W4221150964 @default.
- W4225616484 hasRelatedWork W4288055502 @default.
- W4225616484 isParatext "false" @default.
- W4225616484 isRetracted "false" @default.
- W4225616484 workType "article" @default.