Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037870704> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3037870704 abstract "Imitation Learning is a technique that enables programming the behavior of agents through demonstration, as opposed to manually engineering behavior. However, Imitation Learning methods require demonstration data (in the form of state-action labels) and in many scenarios, the demonstrations can be expensive to obtain or too complex for a demonstrator to execute. This lack or sub-optimality of demonstrations limits the applicability and performance of many Imitation Learning methods. Advancements in Interactive Imitation Learning techniques however, have made it easier for demonstrators to train agents and improve their performance. These techniques involve demonstrators interacting with and guiding the agent as it performs the requisite task. This guidance is typically in the form of corrections or feedback on the current actions being executed by the agent. In this thesis, a novel Interactive Learning technique is proposed that uses human corrective feedback in state-space to train and improve agent behavior. This technique is beneficial since providing guidance to the agent in terms of `changing its state' is often easier or more intuitive for the human demonstrator (as opposed to changing the actions being executed). For instance, in manipulation tasks using a robotic arm, it is easier for the demonstrator to provide state information such as the Cartesian position of the end-effector rather than low-level action information such as joint angles. Keeping such scenarios in mind, we propose our method titled: Teaching Imitative Policies in State-space (TIPS). We evaluate the performance of TIPS for various control tasks as part of the OpenAI Gym toolkit as well as for a manipulation task using a KUKA LBR iiwa robotic arm. We show that through continuous improvement via feedback, agents trained using TIPS outperform the demonstrator and in-turn outperform conventional Imitation Learning agents." @default.
- W3037870704 created "2020-07-02" @default.
- W3037870704 creator A5023965680 @default.
- W3037870704 date "2020-01-01" @default.
- W3037870704 modified "2023-09-26" @default.
- W3037870704 title "Interactive Learning in State-space: Enabling robots to learn from non-expert humans" @default.
- W3037870704 hasPublicationYear "2020" @default.
- W3037870704 type Work @default.
- W3037870704 sameAs 3037870704 @default.
- W3037870704 citedByCount "0" @default.
- W3037870704 crossrefType "journal-article" @default.
- W3037870704 hasAuthorship W3037870704A5023965680 @default.
- W3037870704 hasConcept C105795698 @default.
- W3037870704 hasConcept C107457646 @default.
- W3037870704 hasConcept C11413529 @default.
- W3037870704 hasConcept C121332964 @default.
- W3037870704 hasConcept C126388530 @default.
- W3037870704 hasConcept C127413603 @default.
- W3037870704 hasConcept C154945302 @default.
- W3037870704 hasConcept C15744967 @default.
- W3037870704 hasConcept C201995342 @default.
- W3037870704 hasConcept C2779038628 @default.
- W3037870704 hasConcept C2780451532 @default.
- W3037870704 hasConcept C2780791683 @default.
- W3037870704 hasConcept C33923547 @default.
- W3037870704 hasConcept C41008148 @default.
- W3037870704 hasConcept C48103436 @default.
- W3037870704 hasConcept C62520636 @default.
- W3037870704 hasConcept C72434380 @default.
- W3037870704 hasConcept C77805123 @default.
- W3037870704 hasConcept C90509273 @default.
- W3037870704 hasConcept C97541855 @default.
- W3037870704 hasConceptScore W3037870704C105795698 @default.
- W3037870704 hasConceptScore W3037870704C107457646 @default.
- W3037870704 hasConceptScore W3037870704C11413529 @default.
- W3037870704 hasConceptScore W3037870704C121332964 @default.
- W3037870704 hasConceptScore W3037870704C126388530 @default.
- W3037870704 hasConceptScore W3037870704C127413603 @default.
- W3037870704 hasConceptScore W3037870704C154945302 @default.
- W3037870704 hasConceptScore W3037870704C15744967 @default.
- W3037870704 hasConceptScore W3037870704C201995342 @default.
- W3037870704 hasConceptScore W3037870704C2779038628 @default.
- W3037870704 hasConceptScore W3037870704C2780451532 @default.
- W3037870704 hasConceptScore W3037870704C2780791683 @default.
- W3037870704 hasConceptScore W3037870704C33923547 @default.
- W3037870704 hasConceptScore W3037870704C41008148 @default.
- W3037870704 hasConceptScore W3037870704C48103436 @default.
- W3037870704 hasConceptScore W3037870704C62520636 @default.
- W3037870704 hasConceptScore W3037870704C72434380 @default.
- W3037870704 hasConceptScore W3037870704C77805123 @default.
- W3037870704 hasConceptScore W3037870704C90509273 @default.
- W3037870704 hasConceptScore W3037870704C97541855 @default.
- W3037870704 hasLocation W30378707041 @default.
- W3037870704 hasOpenAccess W3037870704 @default.
- W3037870704 hasPrimaryLocation W30378707041 @default.
- W3037870704 hasRelatedWork W140788646 @default.
- W3037870704 hasRelatedWork W2120982521 @default.
- W3037870704 hasRelatedWork W2589275886 @default.
- W3037870704 hasRelatedWork W2792866523 @default.
- W3037870704 hasRelatedWork W2805810890 @default.
- W3037870704 hasRelatedWork W2933620775 @default.
- W3037870704 hasRelatedWork W2951262671 @default.
- W3037870704 hasRelatedWork W2981233685 @default.
- W3037870704 hasRelatedWork W3046125856 @default.
- W3037870704 hasRelatedWork W304821478 @default.
- W3037870704 hasRelatedWork W3048833305 @default.
- W3037870704 hasRelatedWork W3087903566 @default.
- W3037870704 hasRelatedWork W3091086138 @default.
- W3037870704 hasRelatedWork W3100396494 @default.
- W3037870704 hasRelatedWork W3172303261 @default.
- W3037870704 hasRelatedWork W3202542428 @default.
- W3037870704 hasRelatedWork W3203679646 @default.
- W3037870704 hasRelatedWork W3205478157 @default.
- W3037870704 hasRelatedWork W3206093119 @default.
- W3037870704 hasRelatedWork W79302034 @default.
- W3037870704 isParatext "false" @default.
- W3037870704 isRetracted "false" @default.
- W3037870704 magId "3037870704" @default.
- W3037870704 workType "article" @default.