Matches in SemOpenAlex for { <https://semopenalex.org/work/W2400719195> ?p ?o ?g. }
- W2400719195 abstract "Artificial intelligence is commonly defined as the ability to achieve goals in the world. In the reinforcement learning framework, goals are encoded as reward functions that guide agent behaviour, and the sum of observed rewards provide a notion of progress. However, some domains have no such reward signal, or have a reward signal so sparse as to appear absent. Without reward feedback, agent behaviour is typically random, often dithering aimlessly and lacking intentionality. In this paper we present an algorithm capable of learning purposeful behaviour in the absence of rewards. The algorithm proceeds by constructing temporally extended actions (options), through the identification of purposes that are just out of reach of the agent's current behaviour. These purposes establish intrinsic goals for the agent to learn, ultimately resulting in a suite of behaviours that encourage the agent to visit different parts of the state space. Moreover, the approach is particularly suited for settings where rewards are very sparse, and such behaviours can help in the exploration of the environment until reward is observed." @default.
- W2400719195 created "2016-06-24" @default.
- W2400719195 creator A5081163135 @default.
- W2400719195 creator A5085413987 @default.
- W2400719195 date "2016-05-25" @default.
- W2400719195 modified "2023-09-27" @default.
- W2400719195 title "Learning Purposeful Behaviour in the Absence of Rewards." @default.
- W2400719195 cites W1488730473 @default.
- W2400719195 cites W1536990779 @default.
- W2400719195 cites W1586944634 @default.
- W2400719195 cites W1598052524 @default.
- W2400719195 cites W1949804828 @default.
- W2400719195 cites W2034806191 @default.
- W2400719195 cites W2073384958 @default.
- W2400719195 cites W2090170171 @default.
- W2400719195 cites W2108535023 @default.
- W2400719195 cites W2109910161 @default.
- W2400719195 cites W2114451917 @default.
- W2400719195 cites W2121863487 @default.
- W2400719195 cites W2143435603 @default.
- W2400719195 cites W2145339207 @default.
- W2400719195 cites W2160808139 @default.
- W2400719195 cites W2188721763 @default.
- W2400719195 cites W2335959470 @default.
- W2400719195 cites W2343637401 @default.
- W2400719195 hasPublicationYear "2016" @default.
- W2400719195 type Work @default.
- W2400719195 sameAs 2400719195 @default.
- W2400719195 citedByCount "17" @default.
- W2400719195 countsByYear W24007191952016 @default.
- W2400719195 countsByYear W24007191952017 @default.
- W2400719195 countsByYear W24007191952018 @default.
- W2400719195 countsByYear W24007191952019 @default.
- W2400719195 countsByYear W24007191952020 @default.
- W2400719195 countsByYear W24007191952021 @default.
- W2400719195 crossrefType "posted-content" @default.
- W2400719195 hasAuthorship W2400719195A5081163135 @default.
- W2400719195 hasAuthorship W2400719195A5085413987 @default.
- W2400719195 hasConcept C105795698 @default.
- W2400719195 hasConcept C111472728 @default.
- W2400719195 hasConcept C138885662 @default.
- W2400719195 hasConcept C143661069 @default.
- W2400719195 hasConcept C154945302 @default.
- W2400719195 hasConcept C15744967 @default.
- W2400719195 hasConcept C166957645 @default.
- W2400719195 hasConcept C169760540 @default.
- W2400719195 hasConcept C180747234 @default.
- W2400719195 hasConcept C199360897 @default.
- W2400719195 hasConcept C2777200700 @default.
- W2400719195 hasConcept C2779843651 @default.
- W2400719195 hasConcept C31972630 @default.
- W2400719195 hasConcept C33923547 @default.
- W2400719195 hasConcept C41008148 @default.
- W2400719195 hasConcept C67203356 @default.
- W2400719195 hasConcept C70451592 @default.
- W2400719195 hasConcept C72434380 @default.
- W2400719195 hasConcept C77805123 @default.
- W2400719195 hasConcept C79581498 @default.
- W2400719195 hasConcept C9083635 @default.
- W2400719195 hasConcept C95457728 @default.
- W2400719195 hasConcept C97541855 @default.
- W2400719195 hasConceptScore W2400719195C105795698 @default.
- W2400719195 hasConceptScore W2400719195C111472728 @default.
- W2400719195 hasConceptScore W2400719195C138885662 @default.
- W2400719195 hasConceptScore W2400719195C143661069 @default.
- W2400719195 hasConceptScore W2400719195C154945302 @default.
- W2400719195 hasConceptScore W2400719195C15744967 @default.
- W2400719195 hasConceptScore W2400719195C166957645 @default.
- W2400719195 hasConceptScore W2400719195C169760540 @default.
- W2400719195 hasConceptScore W2400719195C180747234 @default.
- W2400719195 hasConceptScore W2400719195C199360897 @default.
- W2400719195 hasConceptScore W2400719195C2777200700 @default.
- W2400719195 hasConceptScore W2400719195C2779843651 @default.
- W2400719195 hasConceptScore W2400719195C31972630 @default.
- W2400719195 hasConceptScore W2400719195C33923547 @default.
- W2400719195 hasConceptScore W2400719195C41008148 @default.
- W2400719195 hasConceptScore W2400719195C67203356 @default.
- W2400719195 hasConceptScore W2400719195C70451592 @default.
- W2400719195 hasConceptScore W2400719195C72434380 @default.
- W2400719195 hasConceptScore W2400719195C77805123 @default.
- W2400719195 hasConceptScore W2400719195C79581498 @default.
- W2400719195 hasConceptScore W2400719195C9083635 @default.
- W2400719195 hasConceptScore W2400719195C95457728 @default.
- W2400719195 hasConceptScore W2400719195C97541855 @default.
- W2400719195 hasLocation W24007191951 @default.
- W2400719195 hasOpenAccess W2400719195 @default.
- W2400719195 hasPrimaryLocation W24007191951 @default.
- W2400719195 hasRelatedWork W1130790960 @default.
- W2400719195 hasRelatedWork W1536990779 @default.
- W2400719195 hasRelatedWork W1753708795 @default.
- W2400719195 hasRelatedWork W2090170171 @default.
- W2400719195 hasRelatedWork W2108535023 @default.
- W2400719195 hasRelatedWork W2109910161 @default.
- W2400719195 hasRelatedWork W2121517924 @default.
- W2400719195 hasRelatedWork W2121863487 @default.
- W2400719195 hasRelatedWork W2143435603 @default.
- W2400719195 hasRelatedWork W2145339207 @default.
- W2400719195 hasRelatedWork W2166494941 @default.
- W2400719195 hasRelatedWork W2335959470 @default.
- W2400719195 hasRelatedWork W2920768993 @default.