Matches in SemOpenAlex for { <https://semopenalex.org/work/W4363671944> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4363671944 abstract "Hierarchical reinforcement learning is a promising approach that uses temporal abstraction to solve complex long horizon problems. However, simultaneously learning a hierarchy of policies is unstable as it is challenging to train higher-level policy when the lower-level primitive is non-stationary. In this paper, we propose a novel hierarchical algorithm CRISP to generate a curriculum of achievable subgoals for evolving lower-level primitives using reinforcement learning and imitation learning. The lower level primitive periodically performs data relabeling on a handful of expert demonstrations using our primitive informed parsing approach to handle non-stationarity. Since our approach uses a handful of expert demonstrations, it is suitable for most robotic control tasks. Experimental evaluations on complex robotic maze navigation and robotic manipulation environments show that inducing hierarchical curriculum learning significantly improves sample efficiency, and results in efficient goal conditioned policies for solving temporally extended tasks. We perform real world robotic experiments on complex manipulation tasks and demonstrate that CRISP consistently outperforms the baselines." @default.
- W4363671944 created "2023-04-11" @default.
- W4363671944 creator A5007109424 @default.
- W4363671944 creator A5059521481 @default.
- W4363671944 date "2023-04-07" @default.
- W4363671944 modified "2023-09-27" @default.
- W4363671944 title "CRISP: Curriculum inducing Primitive Informed Subgoal Prediction" @default.
- W4363671944 doi "https://doi.org/10.48550/arxiv.2304.03535" @default.
- W4363671944 hasPublicationYear "2023" @default.
- W4363671944 type Work @default.
- W4363671944 citedByCount "0" @default.
- W4363671944 crossrefType "posted-content" @default.
- W4363671944 hasAuthorship W4363671944A5007109424 @default.
- W4363671944 hasAuthorship W4363671944A5059521481 @default.
- W4363671944 hasBestOaLocation W43636719441 @default.
- W4363671944 hasConcept C111472728 @default.
- W4363671944 hasConcept C119857082 @default.
- W4363671944 hasConcept C124304363 @default.
- W4363671944 hasConcept C126388530 @default.
- W4363671944 hasConcept C138885662 @default.
- W4363671944 hasConcept C154945302 @default.
- W4363671944 hasConcept C15744967 @default.
- W4363671944 hasConcept C162324750 @default.
- W4363671944 hasConcept C186644900 @default.
- W4363671944 hasConcept C19417346 @default.
- W4363671944 hasConcept C2775924081 @default.
- W4363671944 hasConcept C31170391 @default.
- W4363671944 hasConcept C34447519 @default.
- W4363671944 hasConcept C41008148 @default.
- W4363671944 hasConcept C47177190 @default.
- W4363671944 hasConcept C77805123 @default.
- W4363671944 hasConcept C97541855 @default.
- W4363671944 hasConceptScore W4363671944C111472728 @default.
- W4363671944 hasConceptScore W4363671944C119857082 @default.
- W4363671944 hasConceptScore W4363671944C124304363 @default.
- W4363671944 hasConceptScore W4363671944C126388530 @default.
- W4363671944 hasConceptScore W4363671944C138885662 @default.
- W4363671944 hasConceptScore W4363671944C154945302 @default.
- W4363671944 hasConceptScore W4363671944C15744967 @default.
- W4363671944 hasConceptScore W4363671944C162324750 @default.
- W4363671944 hasConceptScore W4363671944C186644900 @default.
- W4363671944 hasConceptScore W4363671944C19417346 @default.
- W4363671944 hasConceptScore W4363671944C2775924081 @default.
- W4363671944 hasConceptScore W4363671944C31170391 @default.
- W4363671944 hasConceptScore W4363671944C34447519 @default.
- W4363671944 hasConceptScore W4363671944C41008148 @default.
- W4363671944 hasConceptScore W4363671944C47177190 @default.
- W4363671944 hasConceptScore W4363671944C77805123 @default.
- W4363671944 hasConceptScore W4363671944C97541855 @default.
- W4363671944 hasLocation W43636719441 @default.
- W4363671944 hasOpenAccess W4363671944 @default.
- W4363671944 hasPrimaryLocation W43636719441 @default.
- W4363671944 hasRelatedWork W1564661574 @default.
- W4363671944 hasRelatedWork W1598052524 @default.
- W4363671944 hasRelatedWork W1840287803 @default.
- W4363671944 hasRelatedWork W2502722637 @default.
- W4363671944 hasRelatedWork W2899084033 @default.
- W4363671944 hasRelatedWork W3074294383 @default.
- W4363671944 hasRelatedWork W4319083788 @default.
- W4363671944 hasRelatedWork W4323030201 @default.
- W4363671944 hasRelatedWork W4382239365 @default.
- W4363671944 hasRelatedWork W2744259124 @default.
- W4363671944 isParatext "false" @default.
- W4363671944 isRetracted "false" @default.
- W4363671944 workType "article" @default.