FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2417089653> ?p ?o ?g. }

• W2417089653 abstract "Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternative, called Successor Representations (SR), which decomposes the value function into two components -- a reward predictor and a successor map. The successor map represents the expected future state occupancy from any given state and the reward predictor maps states to scalar rewards. The value function of a state can be computed as the inner product between the successor map and the reward weights. In this paper, we present DSR, which generalizes SR within an end-to-end deep reinforcement learning framework. DSR has several appealing properties including: increased sensitivity to distal reward changes due to factorization of reward and world dynamics, and the ability to extract bottleneck states (subgoals) given successor maps trained under a random policy. We show the efficacy of our approach on two diverse environments given raw pixel observations -- simple grid-world domains (MazeBase) and the Doom game engine." @default.
• W2417089653 created "2016-06-24" @default.
• W2417089653 creator A5031715686 @default.
• W2417089653 creator A5037303942 @default.
• W2417089653 creator A5071817449 @default.
• W2417089653 creator A5091197128 @default.
• W2417089653 date "2016-06-08" @default.
• W2417089653 modified "2023-10-01" @default.
• W2417089653 title "Deep Successor Reinforcement Learning" @default.
• W2417089653 cites W1536990779 @default.
• W2417089653 cites W1658008008 @default.
• W2417089653 cites W1691728462 @default.
• W2417089653 cites W1850742715 @default.
• W2417089653 cites W2001788447 @default.
• W2417089653 cites W2056354534 @default.
• W2417089653 cites W2076546217 @default.
• W2417089653 cites W2090170171 @default.
• W2417089653 cites W2108535023 @default.
• W2417089653 cites W2109910161 @default.
• W2417089653 cites W2111625828 @default.
• W2417089653 cites W2121947440 @default.
• W2417089653 cites W2133105703 @default.
• W2417089653 cites W2143435603 @default.
• W2417089653 cites W2145339207 @default.
• W2417089653 cites W2153894094 @default.
• W2417089653 cites W2159849946 @default.
• W2417089653 cites W2159920598 @default.
• W2417089653 cites W2163176541 @default.
• W2417089653 cites W2174196774 @default.
• W2417089653 cites W2180332918 @default.
• W2417089653 cites W2184099261 @default.
• W2417089653 cites W2201581102 @default.
• W2417089653 cites W2257979135 @default.
• W2417089653 cites W2260756217 @default.
• W2417089653 cites W2274801302 @default.
• W2417089653 cites W2280163991 @default.
• W2417089653 cites W2281112906 @default.
• W2417089653 cites W2327562811 @default.
• W2417089653 cites W2335959470 @default.
• W2417089653 cites W2362143032 @default.
• W2417089653 cites W2400719195 @default.
• W2417089653 cites W2949247522 @default.
• W2417089653 cites W2949497014 @default.
• W2417089653 cites W2962730405 @default.
• W2417089653 cites W567721252 @default.
• W2417089653 cites W779494576 @default.
• W2417089653 hasPublicationYear "2016" @default.
• W2417089653 type Work @default.
• W2417089653 sameAs 2417089653 @default.
• W2417089653 citedByCount "78" @default.
• W2417089653 countsByYear W24170896532016 @default.
• W2417089653 countsByYear W24170896532017 @default.
• W2417089653 countsByYear W24170896532018 @default.
• W2417089653 countsByYear W24170896532019 @default.
• W2417089653 countsByYear W24170896532020 @default.
• W2417089653 countsByYear W24170896532021 @default.
• W2417089653 crossrefType "posted-content" @default.
• W2417089653 hasAuthorship W2417089653A5031715686 @default.
• W2417089653 hasAuthorship W2417089653A5037303942 @default.
• W2417089653 hasAuthorship W2417089653A5071817449 @default.
• W2417089653 hasAuthorship W2417089653A5091197128 @default.
• W2417089653 hasConcept C126255220 @default.
• W2417089653 hasConcept C134306372 @default.
• W2417089653 hasConcept C14646407 @default.
• W2417089653 hasConcept C149635348 @default.
• W2417089653 hasConcept C154945302 @default.
• W2417089653 hasConcept C15744967 @default.
• W2417089653 hasConcept C2780513914 @default.
• W2417089653 hasConcept C33923547 @default.
• W2417089653 hasConcept C41008148 @default.
• W2417089653 hasConcept C67203356 @default.
• W2417089653 hasConcept C75306776 @default.
• W2417089653 hasConcept C77805123 @default.
• W2417089653 hasConcept C97541855 @default.
• W2417089653 hasConceptScore W2417089653C126255220 @default.
• W2417089653 hasConceptScore W2417089653C134306372 @default.
• W2417089653 hasConceptScore W2417089653C14646407 @default.
• W2417089653 hasConceptScore W2417089653C149635348 @default.
• W2417089653 hasConceptScore W2417089653C154945302 @default.
• W2417089653 hasConceptScore W2417089653C15744967 @default.
• W2417089653 hasConceptScore W2417089653C2780513914 @default.
• W2417089653 hasConceptScore W2417089653C33923547 @default.
• W2417089653 hasConceptScore W2417089653C41008148 @default.
• W2417089653 hasConceptScore W2417089653C67203356 @default.
• W2417089653 hasConceptScore W2417089653C75306776 @default.
• W2417089653 hasConceptScore W2417089653C77805123 @default.
• W2417089653 hasConceptScore W2417089653C97541855 @default.
• W2417089653 hasLocation W24170896531 @default.
• W2417089653 hasOpenAccess W2417089653 @default.
• W2417089653 hasPrimaryLocation W24170896531 @default.
• W2417089653 hasRelatedWork W1757796397 @default.
• W2417089653 hasRelatedWork W2056354534 @default.
• W2417089653 hasRelatedWork W2109910161 @default.
• W2417089653 hasRelatedWork W2121863487 @default.
• W2417089653 hasRelatedWork W2145339207 @default.
• W2417089653 hasRelatedWork W2155968351 @default.
• W2417089653 hasRelatedWork W2158782408 @default.
• W2417089653 hasRelatedWork W2257979135 @default.
• W2417089653 hasRelatedWork W2736601468 @default.
• W2417089653 hasRelatedWork W2804673281 @default.

• next