FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3169472801> ?p ?o ?g. }

• W3169472801 abstract "Model-free off-policy actor-critic methods are an efficient solution to complex continuous control tasks. However, these algorithms rely on a number of design tricks and hyperparameters, making their application to new domains difficult and computationally expensive. This paper creates an evolutionary approach that automatically tunes these design decisions and eliminates the RL-specific hyperparameters from the Soft Actor-Critic algorithm. Our design is sample efficient and provides practical advantages over baseline approaches, including improved exploration, generalization over multiple control frequencies, and a robust ensemble of high-performance policies. Empirically, we show that our agent outperforms well-tuned hyperparameter settings in popular benchmarks from the DeepMind Control Suite. We then apply it to less common control tasks outside of simulated robotics to find high-performance solutions with minimal compute and research effort." @default.
• W3169472801 created "2021-06-22" @default.
• W3169472801 creator A5029164534 @default.
• W3169472801 creator A5071517081 @default.
• W3169472801 creator A5078952987 @default.
• W3169472801 date "2021-06-16" @default.
• W3169472801 modified "2023-10-16" @default.
• W3169472801 title "Towards Automatic Actor-Critic Solutions to Continuous Control" @default.
• W3169472801 cites W1191599655 @default.
• W3169472801 cites W2145339207 @default.
• W3169472801 cites W2151083897 @default.
• W3169472801 cites W2158782408 @default.
• W3169472801 cites W2173248099 @default.
• W3169472801 cites W2535915176 @default.
• W3169472801 cites W2596367596 @default.
• W3169472801 cites W2605102581 @default.
• W3169472801 cites W2736601468 @default.
• W3169472801 cites W2754517384 @default.
• W3169472801 cites W2772709170 @default.
• W3169472801 cites W2781585732 @default.
• W3169472801 cites W2781726626 @default.
• W3169472801 cites W2786036274 @default.
• W3169472801 cites W2787938642 @default.
• W3169472801 cites W2798705390 @default.
• W3169472801 cites W2810785043 @default.
• W3169472801 cites W2899205164 @default.
• W3169472801 cites W2904246096 @default.
• W3169472801 cites W2913403708 @default.
• W3169472801 cites W2913773024 @default.
• W3169472801 cites W2950462959 @default.
• W3169472801 cites W2953292661 @default.
• W3169472801 cites W2962755674 @default.
• W3169472801 cites W2963193690 @default.
• W3169472801 cites W2963790038 @default.
• W3169472801 cites W2964043796 @default.
• W3169472801 cites W2964121744 @default.
• W3169472801 cites W2966284335 @default.
• W3169472801 cites W2978644431 @default.
• W3169472801 cites W2991003700 @default.
• W3169472801 cites W3012148463 @default.
• W3169472801 cites W3013618273 @default.
• W3169472801 cites W3034960860 @default.
• W3169472801 cites W3035444337 @default.
• W3169472801 cites W3035466095 @default.
• W3169472801 cites W3038249833 @default.
• W3169472801 cites W3039911048 @default.
• W3169472801 cites W3041764008 @default.
• W3169472801 cites W3042532592 @default.
• W3169472801 cites W3043584299 @default.
• W3169472801 cites W3049177606 @default.
• W3169472801 cites W3087396797 @default.
• W3169472801 cites W3092277419 @default.
• W3169472801 cites W3104819573 @default.
• W3169472801 cites W3107153805 @default.
• W3169472801 cites W3124587580 @default.
• W3169472801 cites W3124816456 @default.
• W3169472801 cites W3126150352 @default.
• W3169472801 cites W3128328080 @default.
• W3169472801 cites W3153480408 @default.
• W3169472801 doi "https://doi.org/10.48550/arxiv.2106.08918" @default.
• W3169472801 hasPublicationYear "2021" @default.
• W3169472801 type Work @default.
• W3169472801 sameAs 3169472801 @default.
• W3169472801 citedByCount "1" @default.
• W3169472801 countsByYear W31694728012021 @default.
• W3169472801 crossrefType "posted-content" @default.
• W3169472801 hasAuthorship W3169472801A5029164534 @default.
• W3169472801 hasAuthorship W3169472801A5071517081 @default.
• W3169472801 hasAuthorship W3169472801A5078952987 @default.
• W3169472801 hasBestOaLocation W31694728011 @default.
• W3169472801 hasConcept C111368507 @default.
• W3169472801 hasConcept C119857082 @default.
• W3169472801 hasConcept C12725497 @default.
• W3169472801 hasConcept C127313418 @default.
• W3169472801 hasConcept C134306372 @default.
• W3169472801 hasConcept C154945302 @default.
• W3169472801 hasConcept C159149176 @default.
• W3169472801 hasConcept C166957645 @default.
• W3169472801 hasConcept C177148314 @default.
• W3169472801 hasConcept C199505168 @default.
• W3169472801 hasConcept C2775924081 @default.
• W3169472801 hasConcept C33923547 @default.
• W3169472801 hasConcept C34413123 @default.
• W3169472801 hasConcept C41008148 @default.
• W3169472801 hasConcept C79581498 @default.
• W3169472801 hasConcept C8642999 @default.
• W3169472801 hasConcept C90509273 @default.
• W3169472801 hasConcept C95457728 @default.
• W3169472801 hasConcept C97541855 @default.
• W3169472801 hasConceptScore W3169472801C111368507 @default.
• W3169472801 hasConceptScore W3169472801C119857082 @default.
• W3169472801 hasConceptScore W3169472801C12725497 @default.
• W3169472801 hasConceptScore W3169472801C127313418 @default.
• W3169472801 hasConceptScore W3169472801C134306372 @default.
• W3169472801 hasConceptScore W3169472801C154945302 @default.
• W3169472801 hasConceptScore W3169472801C159149176 @default.
• W3169472801 hasConceptScore W3169472801C166957645 @default.
• W3169472801 hasConceptScore W3169472801C177148314 @default.
• W3169472801 hasConceptScore W3169472801C199505168 @default.
• W3169472801 hasConceptScore W3169472801C2775924081 @default.

• next