Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216486536> ?p ?o ?g. }
- W3216486536 abstract "The Intelligent decision of the unmanned combat aerial vehicle (UCAV) has long been a challenging problem. The conventional search method can hardly satisfy the real-time demand during high dynamics air combat scenarios. The reinforcement learning (RL) method can significantly shorten the decision time via using neural networks. However, the sparse reward problem limits its convergence speed and the artificial prior experience reward can easily deviate its optimal convergent direction of the original task, which raises great difficulties for the RL air combat application. In this paper, we propose a homotopy-based soft actor-critic method (HSAC) which focuses on addressing these problems via following the homotopy path between the original task with sparse reward and the auxiliary task with artificial prior experience reward. The convergence and the feasibility of this method are also proved in this paper. To confirm our method feasibly, we construct a detailed 3D air combat simulation environment for the RL-based methods training firstly, and we implement our method in both the attack horizontal flight UCAV task and the self-play confrontation task. Experimental results show that our method performs better than the methods only utilizing the sparse reward or the artificial prior experience reward. The agent trained by our method can reach more than 98.3% win rate in the attack horizontal flight UCAV task and average 67.4% win rate when confronted with the agents trained by the other two methods." @default.
- W3216486536 created "2021-12-06" @default.
- W3216486536 creator A5017400481 @default.
- W3216486536 creator A5057415739 @default.
- W3216486536 creator A5071045573 @default.
- W3216486536 creator A5077325580 @default.
- W3216486536 date "2021-12-01" @default.
- W3216486536 modified "2023-09-27" @default.
- W3216486536 title "Homotopy Based Reinforcement Learning with Maximum Entropy for Autonomous Air Combat" @default.
- W3216486536 cites W1489065448 @default.
- W3216486536 cites W1499408472 @default.
- W3216486536 cites W1503228476 @default.
- W3216486536 cites W1540986431 @default.
- W3216486536 cites W163161797 @default.
- W3216486536 cites W1777239053 @default.
- W3216486536 cites W1995875735 @default.
- W3216486536 cites W2008534448 @default.
- W3216486536 cites W2012392077 @default.
- W3216486536 cites W2014229971 @default.
- W3216486536 cites W2014746566 @default.
- W3216486536 cites W2075110355 @default.
- W3216486536 cites W2084342013 @default.
- W3216486536 cites W2098774185 @default.
- W3216486536 cites W2107151099 @default.
- W3216486536 cites W2121863487 @default.
- W3216486536 cites W2129798991 @default.
- W3216486536 cites W2330024298 @default.
- W3216486536 cites W2348215975 @default.
- W3216486536 cites W2386148433 @default.
- W3216486536 cites W2515894276 @default.
- W3216486536 cites W2575705757 @default.
- W3216486536 cites W2594103415 @default.
- W3216486536 cites W2726187156 @default.
- W3216486536 cites W2741122588 @default.
- W3216486536 cites W2744921630 @default.
- W3216486536 cites W2755174311 @default.
- W3216486536 cites W2897500832 @default.
- W3216486536 cites W2904246096 @default.
- W3216486536 cites W2913448405 @default.
- W3216486536 cites W2962902376 @default.
- W3216486536 cites W2962957031 @default.
- W3216486536 cites W2963133245 @default.
- W3216486536 cites W2963630259 @default.
- W3216486536 cites W2963923407 @default.
- W3216486536 cites W2998655286 @default.
- W3216486536 cites W3039802322 @default.
- W3216486536 cites W3041508111 @default.
- W3216486536 cites W3127872041 @default.
- W3216486536 cites W7859117 @default.
- W3216486536 doi "https://doi.org/10.48550/arxiv.2112.01328" @default.
- W3216486536 hasPublicationYear "2021" @default.
- W3216486536 type Work @default.
- W3216486536 sameAs 3216486536 @default.
- W3216486536 citedByCount "0" @default.
- W3216486536 crossrefType "posted-content" @default.
- W3216486536 hasAuthorship W3216486536A5017400481 @default.
- W3216486536 hasAuthorship W3216486536A5057415739 @default.
- W3216486536 hasAuthorship W3216486536A5071045573 @default.
- W3216486536 hasAuthorship W3216486536A5077325580 @default.
- W3216486536 hasBestOaLocation W32164865361 @default.
- W3216486536 hasConcept C106301342 @default.
- W3216486536 hasConcept C119857082 @default.
- W3216486536 hasConcept C121332964 @default.
- W3216486536 hasConcept C127162648 @default.
- W3216486536 hasConcept C127413603 @default.
- W3216486536 hasConcept C154945302 @default.
- W3216486536 hasConcept C162324750 @default.
- W3216486536 hasConcept C201995342 @default.
- W3216486536 hasConcept C202444582 @default.
- W3216486536 hasConcept C2777303404 @default.
- W3216486536 hasConcept C2780451532 @default.
- W3216486536 hasConcept C2988296547 @default.
- W3216486536 hasConcept C31258907 @default.
- W3216486536 hasConcept C33923547 @default.
- W3216486536 hasConcept C41008148 @default.
- W3216486536 hasConcept C44154836 @default.
- W3216486536 hasConcept C50522688 @default.
- W3216486536 hasConcept C57869625 @default.
- W3216486536 hasConcept C5961521 @default.
- W3216486536 hasConcept C62520636 @default.
- W3216486536 hasConcept C97541855 @default.
- W3216486536 hasConceptScore W3216486536C106301342 @default.
- W3216486536 hasConceptScore W3216486536C119857082 @default.
- W3216486536 hasConceptScore W3216486536C121332964 @default.
- W3216486536 hasConceptScore W3216486536C127162648 @default.
- W3216486536 hasConceptScore W3216486536C127413603 @default.
- W3216486536 hasConceptScore W3216486536C154945302 @default.
- W3216486536 hasConceptScore W3216486536C162324750 @default.
- W3216486536 hasConceptScore W3216486536C201995342 @default.
- W3216486536 hasConceptScore W3216486536C202444582 @default.
- W3216486536 hasConceptScore W3216486536C2777303404 @default.
- W3216486536 hasConceptScore W3216486536C2780451532 @default.
- W3216486536 hasConceptScore W3216486536C2988296547 @default.
- W3216486536 hasConceptScore W3216486536C31258907 @default.
- W3216486536 hasConceptScore W3216486536C33923547 @default.
- W3216486536 hasConceptScore W3216486536C41008148 @default.
- W3216486536 hasConceptScore W3216486536C44154836 @default.
- W3216486536 hasConceptScore W3216486536C50522688 @default.
- W3216486536 hasConceptScore W3216486536C57869625 @default.
- W3216486536 hasConceptScore W3216486536C5961521 @default.