FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2616430965> ?p ?o ?g. }

• W2616430965 abstract "Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such an approach does not scale well to settings in which an agent needs to perform a diverse set of tasks, such as navigating to varying positions in a room or moving objects to varying locations. Instead, we propose a method that allows an agent to automatically discover the range of tasks that it is capable of performing. We use a generator network to propose tasks for the agent to try to achieve, specified as goal states. The generator network is optimized using adversarial training to produce tasks that are always at the appropriate level of difficulty for the agent. Our method thus automatically produces a curriculum of tasks for the agent to learn. We show that, by using this framework, an agent can efficiently and automatically learn to perform a wide set of tasks without requiring any prior knowledge of its environment. Our method can also learn to achieve tasks with sparse rewards, which traditionally pose significant challenges." @default.
• W2616430965 created "2017-05-26" @default.
• W2616430965 creator A5001534200 @default.
• W2616430965 creator A5037048516 @default.
• W2616430965 creator A5049349154 @default.
• W2616430965 creator A5081645573 @default.
• W2616430965 date "2017-05-17" @default.
• W2616430965 modified "2023-09-27" @default.
• W2616430965 title "Automatic Goal Generation for Reinforcement Learning Agents" @default.
• W2616430965 cites W1191599655 @default.
• W2616430965 cites W1581407678 @default.
• W2616430965 cites W1710476689 @default.
• W2616430965 cites W1777239053 @default.
• W2616430965 cites W1863227302 @default.
• W2616430965 cites W1969074599 @default.
• W2616430965 cites W1991247894 @default.
• W2616430965 cites W2004303440 @default.
• W2616430965 cites W2012587148 @default.
• W2616430965 cites W2034806191 @default.
• W2616430965 cites W2099471712 @default.
• W2616430965 cites W2122480991 @default.
• W2616430965 cites W2132984949 @default.
• W2616430965 cites W2135354436 @default.
• W2616430965 cites W2145339207 @default.
• W2616430965 cites W2158641818 @default.
• W2616430965 cites W2158782408 @default.
• W2616430965 cites W2173248099 @default.
• W2616430965 cites W2211996086 @default.
• W2616430965 cites W2256388387 @default.
• W2616430965 cites W2257979135 @default.
• W2616430965 cites W2258731934 @default.
• W2616430965 cites W2285664202 @default.
• W2616430965 cites W2296073425 @default.
• W2616430965 cites W2342662072 @default.
• W2616430965 cites W2417786368 @default.
• W2616430965 cites W2419612459 @default.
• W2616430965 cites W2442341664 @default.
• W2616430965 cites W2534060593 @default.
• W2616430965 cites W2553756201 @default.
• W2616430965 cites W2590567779 @default.
• W2616430965 cites W2593766708 @default.
• W2616430965 cites W2603088459 @default.
• W2616430965 cites W2605801332 @default.
• W2616430965 cites W2606433045 @default.
• W2616430965 cites W2680401079 @default.
• W2616430965 cites W2733961795 @default.
• W2616430965 cites W2777298534 @default.
• W2616430965 cites W2949248709 @default.
• W2616430965 cites W2949475445 @default.
• W2616430965 cites W2949496494 @default.
• W2616430965 cites W2949608212 @default.
• W2616430965 cites W2950304420 @default.
• W2616430965 cites W2963293881 @default.
• W2616430965 cites W2964161785 @default.
• W2616430965 cites W567721252 @default.
• W2616430965 cites W59183349 @default.
• W2616430965 hasPublicationYear "2017" @default.
• W2616430965 type Work @default.
• W2616430965 sameAs 2616430965 @default.
• W2616430965 citedByCount "36" @default.
• W2616430965 countsByYear W26164309652017 @default.
• W2616430965 countsByYear W26164309652018 @default.
• W2616430965 countsByYear W26164309652019 @default.
• W2616430965 countsByYear W26164309652020 @default.
• W2616430965 countsByYear W26164309652021 @default.
• W2616430965 crossrefType "posted-content" @default.
• W2616430965 hasAuthorship W2616430965A5001534200 @default.
• W2616430965 hasAuthorship W2616430965A5037048516 @default.
• W2616430965 hasAuthorship W2616430965A5049349154 @default.
• W2616430965 hasAuthorship W2616430965A5081645573 @default.
• W2616430965 hasConcept C107457646 @default.
• W2616430965 hasConcept C119857082 @default.
• W2616430965 hasConcept C121332964 @default.
• W2616430965 hasConcept C127413603 @default.
• W2616430965 hasConcept C14036430 @default.
• W2616430965 hasConcept C146978453 @default.
• W2616430965 hasConcept C154945302 @default.
• W2616430965 hasConcept C163258240 @default.
• W2616430965 hasConcept C177264268 @default.
• W2616430965 hasConcept C199360897 @default.
• W2616430965 hasConcept C201995342 @default.
• W2616430965 hasConcept C204323151 @default.
• W2616430965 hasConcept C2780451532 @default.
• W2616430965 hasConcept C2780992000 @default.
• W2616430965 hasConcept C41008148 @default.
• W2616430965 hasConcept C62520636 @default.
• W2616430965 hasConcept C78458016 @default.
• W2616430965 hasConcept C86803240 @default.
• W2616430965 hasConcept C97541855 @default.
• W2616430965 hasConceptScore W2616430965C107457646 @default.
• W2616430965 hasConceptScore W2616430965C119857082 @default.
• W2616430965 hasConceptScore W2616430965C121332964 @default.
• W2616430965 hasConceptScore W2616430965C127413603 @default.
• W2616430965 hasConceptScore W2616430965C14036430 @default.
• W2616430965 hasConceptScore W2616430965C146978453 @default.
• W2616430965 hasConceptScore W2616430965C154945302 @default.
• W2616430965 hasConceptScore W2616430965C163258240 @default.
• W2616430965 hasConceptScore W2616430965C177264268 @default.
• W2616430965 hasConceptScore W2616430965C199360897 @default.
• W2616430965 hasConceptScore W2616430965C201995342 @default.

• next