FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893841966> ?p ?o ?g. }

• W2893841966 abstract "Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for such tasks: model-free or model-based. Each of these approaches has limitations. Model-free RL struggles to transfer learned information when the goal location changes, but achieves high asymptotic accuracy in single goal tasks. Model-based RL can transfer learned information to new goal locations by retaining the explicitly learned state-dynamics, but is limited by the fact that small errors in modelling these dynamics accumulate over long-term planning. In this work, we improve upon the limitations of model-free RL in multi-goal domains. We do this by adapting the Floyd-Warshall algorithm for RL and call the adaptation Floyd-Warshall RL (FWRL). The proposed algorithm learns a goal-conditioned action-value function by constraining the value of the optimal path between any two states to be greater than or equal to the value of paths via intermediary states. Experimentally, we show that FWRL is more sample-efficient and learns higher reward strategies in multi-goal tasks as compared to Q-learning, model-based RL and other relevant baselines in a tabular domain." @default.
• W2893841966 created "2018-10-05" @default.
• W2893841966 creator A5001804680 @default.
• W2893841966 creator A5033777391 @default.
• W2893841966 creator A5079140683 @default.
• W2893841966 creator A5079301873 @default.
• W2893841966 date "2018-09-25" @default.
• W2893841966 modified "2023-09-27" @default.
• W2893841966 title "Floyd-Warshall Reinforcement Learning Learning from Past Experiences to Reach New Goals" @default.
• W2893841966 cites W1594201624 @default.
• W2893841966 cites W2007572995 @default.
• W2893841966 cites W2022980325 @default.
• W2893841966 cites W2169528473 @default.
• W2893841966 cites W2261254692 @default.
• W2893841966 cites W2418628973 @default.
• W2893841966 cites W2567015638 @default.
• W2893841966 cites W2593841437 @default.
• W2893841966 cites W2594903727 @default.
• W2893841966 cites W2785389871 @default.
• W2893841966 cites W2786658125 @default.
• W2893841966 cites W2889347284 @default.
• W2893841966 cites W2962736495 @default.
• W2893841966 cites W2962759351 @default.
• W2893841966 cites W2962887844 @default.
• W2893841966 cites W2963238274 @default.
• W2893841966 cites W2963245725 @default.
• W2893841966 cites W2963775850 @default.
• W2893841966 cites W2963800628 @default.
• W2893841966 cites W2963946945 @default.
• W2893841966 cites W2964036701 @default.
• W2893841966 cites W567721252 @default.
• W2893841966 hasPublicationYear "2018" @default.
• W2893841966 type Work @default.
• W2893841966 sameAs 2893841966 @default.
• W2893841966 citedByCount "9" @default.
• W2893841966 countsByYear W28938419662019 @default.
• W2893841966 countsByYear W28938419662020 @default.
• W2893841966 countsByYear W28938419662021 @default.
• W2893841966 crossrefType "posted-content" @default.
• W2893841966 hasAuthorship W2893841966A5001804680 @default.
• W2893841966 hasAuthorship W2893841966A5033777391 @default.
• W2893841966 hasAuthorship W2893841966A5079140683 @default.
• W2893841966 hasAuthorship W2893841966A5079301873 @default.
• W2893841966 hasConcept C119857082 @default.
• W2893841966 hasConcept C120665830 @default.
• W2893841966 hasConcept C121332964 @default.
• W2893841966 hasConcept C126255220 @default.
• W2893841966 hasConcept C134306372 @default.
• W2893841966 hasConcept C139807058 @default.
• W2893841966 hasConcept C14036430 @default.
• W2893841966 hasConcept C14646407 @default.
• W2893841966 hasConcept C150899416 @default.
• W2893841966 hasConcept C154945302 @default.
• W2893841966 hasConcept C199360897 @default.
• W2893841966 hasConcept C2777735758 @default.
• W2893841966 hasConcept C33923547 @default.
• W2893841966 hasConcept C34413123 @default.
• W2893841966 hasConcept C36503486 @default.
• W2893841966 hasConcept C41008148 @default.
• W2893841966 hasConcept C78458016 @default.
• W2893841966 hasConcept C86803240 @default.
• W2893841966 hasConcept C90509273 @default.
• W2893841966 hasConcept C97541855 @default.
• W2893841966 hasConceptScore W2893841966C119857082 @default.
• W2893841966 hasConceptScore W2893841966C120665830 @default.
• W2893841966 hasConceptScore W2893841966C121332964 @default.
• W2893841966 hasConceptScore W2893841966C126255220 @default.
• W2893841966 hasConceptScore W2893841966C134306372 @default.
• W2893841966 hasConceptScore W2893841966C139807058 @default.
• W2893841966 hasConceptScore W2893841966C14036430 @default.
• W2893841966 hasConceptScore W2893841966C14646407 @default.
• W2893841966 hasConceptScore W2893841966C150899416 @default.
• W2893841966 hasConceptScore W2893841966C154945302 @default.
• W2893841966 hasConceptScore W2893841966C199360897 @default.
• W2893841966 hasConceptScore W2893841966C2777735758 @default.
• W2893841966 hasConceptScore W2893841966C33923547 @default.
• W2893841966 hasConceptScore W2893841966C34413123 @default.
• W2893841966 hasConceptScore W2893841966C36503486 @default.
• W2893841966 hasConceptScore W2893841966C41008148 @default.
• W2893841966 hasConceptScore W2893841966C78458016 @default.
• W2893841966 hasConceptScore W2893841966C86803240 @default.
• W2893841966 hasConceptScore W2893841966C90509273 @default.
• W2893841966 hasConceptScore W2893841966C97541855 @default.
• W2893841966 hasLocation W28938419661 @default.
• W2893841966 hasOpenAccess W2893841966 @default.
• W2893841966 hasPrimaryLocation W28938419661 @default.
• W2893841966 hasRelatedWork W1526807135 @default.
• W2893841966 hasRelatedWork W1594201624 @default.
• W2893841966 hasRelatedWork W2097797606 @default.
• W2893841966 hasRelatedWork W2109910161 @default.
• W2893841966 hasRelatedWork W2289410116 @default.
• W2893841966 hasRelatedWork W2756826236 @default.
• W2893841966 hasRelatedWork W2936107880 @default.
• W2893841966 hasRelatedWork W2945090640 @default.
• W2893841966 hasRelatedWork W2964001908 @default.
• W2893841966 hasRelatedWork W3008970887 @default.
• W2893841966 hasRelatedWork W3036054814 @default.
• W2893841966 hasRelatedWork W3037476194 @default.
• W2893841966 hasRelatedWork W3045402999 @default.
• W2893841966 hasRelatedWork W3046755562 @default.

• next