Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280496778> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4280496778 abstract "In this paper we analyze the qualitative differences between evolutionary strategies and reinforcement learning algorithms by focusing on two popular state-of-the-art algorithms: the OpenAI-ES evolutionary strategy and the Proximal Policy Optimization (PPO) reinforcement learning algorithm -- the most similar methods of the two families. We analyze how the methods differ with respect to: (i) general efficacy, (ii) ability to cope with sparse rewards, (iii) propensity/capacity to discover minimal solutions, (iv) dependency on reward shaping, and (v) ability to cope with variations of the environmental conditions. The analysis of the performance and of the behavioral strategies displayed by the agents trained with the two methods on benchmark problems enable us to demonstrate qualitative differences which were not identified in previous studies, to identify the relative weakness of the two methods, and to propose ways to ameliorate some of those weakness. We show that the characteristics of the reward function has a strong impact which vary qualitatively not only for the OpenAI-ES and the PPO but also for alternative reinforcement learning algorithms, thus demonstrating the importance of optimizing the characteristic of the reward function to the algorithm used." @default.
- W4280496778 created "2022-05-22" @default.
- W4280496778 creator A5022836666 @default.
- W4280496778 creator A5090304213 @default.
- W4280496778 date "2022-05-16" @default.
- W4280496778 modified "2023-09-26" @default.
- W4280496778 title "Qualitative Differences Between Evolutionary Strategies and Reinforcement Learning Methods for Control of Autonomous Agents" @default.
- W4280496778 doi "https://doi.org/10.48550/arxiv.2205.07592" @default.
- W4280496778 hasPublicationYear "2022" @default.
- W4280496778 type Work @default.
- W4280496778 citedByCount "0" @default.
- W4280496778 crossrefType "posted-content" @default.
- W4280496778 hasAuthorship W4280496778A5022836666 @default.
- W4280496778 hasAuthorship W4280496778A5090304213 @default.
- W4280496778 hasBestOaLocation W42804967781 @default.
- W4280496778 hasConcept C119857082 @default.
- W4280496778 hasConcept C13280743 @default.
- W4280496778 hasConcept C14036430 @default.
- W4280496778 hasConcept C154945302 @default.
- W4280496778 hasConcept C15744967 @default.
- W4280496778 hasConcept C185798385 @default.
- W4280496778 hasConcept C19768560 @default.
- W4280496778 hasConcept C205649164 @default.
- W4280496778 hasConcept C2775924081 @default.
- W4280496778 hasConcept C41008148 @default.
- W4280496778 hasConcept C67203356 @default.
- W4280496778 hasConcept C77805123 @default.
- W4280496778 hasConcept C78458016 @default.
- W4280496778 hasConcept C86803240 @default.
- W4280496778 hasConcept C97541855 @default.
- W4280496778 hasConceptScore W4280496778C119857082 @default.
- W4280496778 hasConceptScore W4280496778C13280743 @default.
- W4280496778 hasConceptScore W4280496778C14036430 @default.
- W4280496778 hasConceptScore W4280496778C154945302 @default.
- W4280496778 hasConceptScore W4280496778C15744967 @default.
- W4280496778 hasConceptScore W4280496778C185798385 @default.
- W4280496778 hasConceptScore W4280496778C19768560 @default.
- W4280496778 hasConceptScore W4280496778C205649164 @default.
- W4280496778 hasConceptScore W4280496778C2775924081 @default.
- W4280496778 hasConceptScore W4280496778C41008148 @default.
- W4280496778 hasConceptScore W4280496778C67203356 @default.
- W4280496778 hasConceptScore W4280496778C77805123 @default.
- W4280496778 hasConceptScore W4280496778C78458016 @default.
- W4280496778 hasConceptScore W4280496778C86803240 @default.
- W4280496778 hasConceptScore W4280496778C97541855 @default.
- W4280496778 hasLocation W42804967781 @default.
- W4280496778 hasLocation W42804967782 @default.
- W4280496778 hasOpenAccess W4280496778 @default.
- W4280496778 hasPrimaryLocation W42804967781 @default.
- W4280496778 hasRelatedWork W1485630101 @default.
- W4280496778 hasRelatedWork W2151702863 @default.
- W4280496778 hasRelatedWork W3022038857 @default.
- W4280496778 hasRelatedWork W3095449511 @default.
- W4280496778 hasRelatedWork W3132110306 @default.
- W4280496778 hasRelatedWork W3153007185 @default.
- W4280496778 hasRelatedWork W4210912933 @default.
- W4280496778 hasRelatedWork W4296474751 @default.
- W4280496778 hasRelatedWork W4319083788 @default.
- W4280496778 hasRelatedWork W63071447 @default.
- W4280496778 isParatext "false" @default.
- W4280496778 isRetracted "false" @default.
- W4280496778 workType "article" @default.