Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912187182> ?p ?o ?g. }
- W2912187182 endingPage "1142" @default.
- W2912187182 startingPage "1134" @default.
- W2912187182 abstract "Reinforcement learning (RL) has proven to be a powerful paradigm for deriving complex behaviors from simple reward signals in a wide range of environments. When applying RL to continuous control agents in simulated physics environments, the body is usually considered to be part of the environment. However, during evolution the physical body of biological organisms and their controlling brains are co-evolved, thus exploring a much larger space of actuator/controller configurations. Put differently, the intelligence does not reside only in the agent's mind, but also in the design of their body. We propose a method for uncovering strong agents, consisting of a good combination of a body and policy, based on combining RL with an evolutionary procedure. Given the resulting agent, we also propose an approach for identifying the body changes that contributed the most to the agent performance. We use the Shapley value from cooperative game theory to find the fair contribution of individual components, taking into account synergies between components. We evaluate our methods in an environment similar to the the recently proposed Robo-Sumo task, where agents in a software physics simulator compete in tipping over their opponent or pushing them out of the arena. Our results show that the proposed methods are indeed capable of generating strong agents, significantly outperforming baselines that focus on optimizing the agent policy alone. A video is available at: https://youtu.be/CHlecRim9PI" @default.
- W2912187182 created "2019-02-21" @default.
- W2912187182 creator A5011829015 @default.
- W2912187182 creator A5013834379 @default.
- W2912187182 creator A5030271887 @default.
- W2912187182 creator A5031943811 @default.
- W2912187182 creator A5045898861 @default.
- W2912187182 creator A5051619646 @default.
- W2912187182 creator A5062949033 @default.
- W2912187182 creator A5062951341 @default.
- W2912187182 date "2019-05-08" @default.
- W2912187182 modified "2023-09-23" @default.
- W2912187182 title "The Body is Not a Given: Joint Agent Policy Learning and Morphology Evolution" @default.
- W2912187182 cites W1504962226 @default.
- W2912187182 cites W1506888295 @default.
- W2912187182 cites W1542941925 @default.
- W2912187182 cites W1562353621 @default.
- W2912187182 cites W1596984324 @default.
- W2912187182 cites W1597864774 @default.
- W2912187182 cites W1601787291 @default.
- W2912187182 cites W1771410628 @default.
- W2912187182 cites W1908253641 @default.
- W2912187182 cites W1940940654 @default.
- W2912187182 cites W1968958679 @default.
- W2912187182 cites W1977655452 @default.
- W2912187182 cites W1983449914 @default.
- W2912187182 cites W2012359374 @default.
- W2912187182 cites W2071232943 @default.
- W2912187182 cites W2088956500 @default.
- W2912187182 cites W2102038059 @default.
- W2912187182 cites W2103691541 @default.
- W2912187182 cites W2117085697 @default.
- W2912187182 cites W2117843694 @default.
- W2912187182 cites W2118832894 @default.
- W2912187182 cites W2120652436 @default.
- W2912187182 cites W2143039680 @default.
- W2912187182 cites W2145339207 @default.
- W2912187182 cites W2158782408 @default.
- W2912187182 cites W2257979135 @default.
- W2912187182 cites W2277908906 @default.
- W2912187182 cites W2334394966 @default.
- W2912187182 cites W2411690432 @default.
- W2912187182 cites W2503389082 @default.
- W2912187182 cites W2510508396 @default.
- W2912187182 cites W2525614878 @default.
- W2912187182 cites W2575731723 @default.
- W2912187182 cites W2726187156 @default.
- W2912187182 cites W2735468692 @default.
- W2912187182 cites W2736601468 @default.
- W2912187182 cites W2757631751 @default.
- W2912187182 cites W2762872434 @default.
- W2912187182 cites W2767002384 @default.
- W2912187182 cites W2785342287 @default.
- W2912187182 cites W2884925072 @default.
- W2912187182 cites W2943307976 @default.
- W2912187182 cites W2964006217 @default.
- W2912187182 cites W2964161785 @default.
- W2912187182 hasPublicationYear "2019" @default.
- W2912187182 type Work @default.
- W2912187182 sameAs 2912187182 @default.
- W2912187182 citedByCount "3" @default.
- W2912187182 countsByYear W29121871822020 @default.
- W2912187182 countsByYear W29121871822021 @default.
- W2912187182 crossrefType "proceedings-article" @default.
- W2912187182 hasAuthorship W2912187182A5011829015 @default.
- W2912187182 hasAuthorship W2912187182A5013834379 @default.
- W2912187182 hasAuthorship W2912187182A5030271887 @default.
- W2912187182 hasAuthorship W2912187182A5031943811 @default.
- W2912187182 hasAuthorship W2912187182A5045898861 @default.
- W2912187182 hasAuthorship W2912187182A5051619646 @default.
- W2912187182 hasAuthorship W2912187182A5062949033 @default.
- W2912187182 hasAuthorship W2912187182A5062951341 @default.
- W2912187182 hasConcept C107457646 @default.
- W2912187182 hasConcept C111472728 @default.
- W2912187182 hasConcept C111919701 @default.
- W2912187182 hasConcept C120314980 @default.
- W2912187182 hasConcept C120665830 @default.
- W2912187182 hasConcept C121332964 @default.
- W2912187182 hasConcept C127413603 @default.
- W2912187182 hasConcept C136197465 @default.
- W2912187182 hasConcept C138885662 @default.
- W2912187182 hasConcept C146978453 @default.
- W2912187182 hasConcept C154945302 @default.
- W2912187182 hasConcept C192209626 @default.
- W2912187182 hasConcept C201995342 @default.
- W2912187182 hasConcept C203479927 @default.
- W2912187182 hasConcept C204323151 @default.
- W2912187182 hasConcept C2778572836 @default.
- W2912187182 hasConcept C2780451532 @default.
- W2912187182 hasConcept C2780586882 @default.
- W2912187182 hasConcept C38652104 @default.
- W2912187182 hasConcept C41008148 @default.
- W2912187182 hasConcept C41065033 @default.
- W2912187182 hasConcept C6557445 @default.
- W2912187182 hasConcept C86803240 @default.
- W2912187182 hasConcept C97541855 @default.
- W2912187182 hasConceptScore W2912187182C107457646 @default.
- W2912187182 hasConceptScore W2912187182C111472728 @default.