FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999596312> ?p ?o ?g. }

• W2999596312 abstract "In this paper, a novel racing environment for OpenAI Gym is introduced. This environment operates with continuous action- and state-spaces and requires agents to learn to control the acceleration and steering of a car while navigating a randomly generated racetrack. Different versions of two actor-critic learning algorithms are tested on this environment: Sampled Policy Gradient (SPG) and Proximal Policy Optimization (PPO). An extension of SPG is introduced that aims to improve learning performance by weighting action samples during the policy update step. The effect of using experience replay (ER) is also investigated. To this end, a modification to PPO is introduced that allows for training using old action samples by optimizing the actor in log space. Finally, a new technique for performing ER is tested that aims to improve learning speed without sacrificing performance by splitting the training into two parts, whereby networks are first trained using state transitions from the replay buffer, and then using only recent experiences. The results indicate that experience replay is not beneficial to PPO in continuous action spaces. The training of SPG seems to be more stable when actions are weighted. All versions of SPG outperform PPO when ER is used. The ER trick is effective at improving training speed on a computationally less intensive version of SPG." @default.
• W2999596312 created "2020-01-23" @default.
• W2999596312 creator A5021463358 @default.
• W2999596312 creator A5060596453 @default.
• W2999596312 date "2020-01-15" @default.
• W2999596312 modified "2023-09-27" @default.
• W2999596312 title "Continuous-action Reinforcement Learning for Playing Racing Games: Comparing SPG to PPO" @default.
• W2999596312 cites W1488133609 @default.
• W2999596312 cites W1595483645 @default.
• W2999596312 cites W1757796397 @default.
• W2999596312 cites W1771410628 @default.
• W2999596312 cites W1993411524 @default.
• W2999596312 cites W2101539915 @default.
• W2999596312 cites W2121863487 @default.
• W2999596312 cites W2165150801 @default.
• W2999596312 cites W2201581102 @default.
• W2999596312 cites W2290354866 @default.
• W2999596312 cites W2574473771 @default.
• W2999596312 cites W2727576081 @default.
• W2999596312 cites W2736601468 @default.
• W2999596312 cites W2891716277 @default.
• W2999596312 cites W2949608212 @default.
• W2999596312 hasPublicationYear "2020" @default.
• W2999596312 type Work @default.
• W2999596312 sameAs 2999596312 @default.
• W2999596312 citedByCount "0" @default.
• W2999596312 crossrefType "posted-content" @default.
• W2999596312 hasAuthorship W2999596312A5021463358 @default.
• W2999596312 hasAuthorship W2999596312A5060596453 @default.
• W2999596312 hasConcept C105795698 @default.
• W2999596312 hasConcept C111919701 @default.
• W2999596312 hasConcept C11413529 @default.
• W2999596312 hasConcept C117896860 @default.
• W2999596312 hasConcept C119857082 @default.
• W2999596312 hasConcept C121332964 @default.
• W2999596312 hasConcept C126838900 @default.
• W2999596312 hasConcept C153294291 @default.
• W2999596312 hasConcept C154945302 @default.
• W2999596312 hasConcept C183115368 @default.
• W2999596312 hasConcept C199360897 @default.
• W2999596312 hasConcept C2775924081 @default.
• W2999596312 hasConcept C2777211547 @default.
• W2999596312 hasConcept C2778029271 @default.
• W2999596312 hasConcept C2778572836 @default.
• W2999596312 hasConcept C2780791683 @default.
• W2999596312 hasConcept C33923547 @default.
• W2999596312 hasConcept C41008148 @default.
• W2999596312 hasConcept C48103436 @default.
• W2999596312 hasConcept C62520636 @default.
• W2999596312 hasConcept C71924100 @default.
• W2999596312 hasConcept C72434380 @default.
• W2999596312 hasConcept C74650414 @default.
• W2999596312 hasConcept C97541855 @default.
• W2999596312 hasConceptScore W2999596312C105795698 @default.
• W2999596312 hasConceptScore W2999596312C111919701 @default.
• W2999596312 hasConceptScore W2999596312C11413529 @default.
• W2999596312 hasConceptScore W2999596312C117896860 @default.
• W2999596312 hasConceptScore W2999596312C119857082 @default.
• W2999596312 hasConceptScore W2999596312C121332964 @default.
• W2999596312 hasConceptScore W2999596312C126838900 @default.
• W2999596312 hasConceptScore W2999596312C153294291 @default.
• W2999596312 hasConceptScore W2999596312C154945302 @default.
• W2999596312 hasConceptScore W2999596312C183115368 @default.
• W2999596312 hasConceptScore W2999596312C199360897 @default.
• W2999596312 hasConceptScore W2999596312C2775924081 @default.
• W2999596312 hasConceptScore W2999596312C2777211547 @default.
• W2999596312 hasConceptScore W2999596312C2778029271 @default.
• W2999596312 hasConceptScore W2999596312C2778572836 @default.
• W2999596312 hasConceptScore W2999596312C2780791683 @default.
• W2999596312 hasConceptScore W2999596312C33923547 @default.
• W2999596312 hasConceptScore W2999596312C41008148 @default.
• W2999596312 hasConceptScore W2999596312C48103436 @default.
• W2999596312 hasConceptScore W2999596312C62520636 @default.
• W2999596312 hasConceptScore W2999596312C71924100 @default.
• W2999596312 hasConceptScore W2999596312C72434380 @default.
• W2999596312 hasConceptScore W2999596312C74650414 @default.
• W2999596312 hasConceptScore W2999596312C97541855 @default.
• W2999596312 hasOpenAccess W2999596312 @default.
• W2999596312 hasRelatedWork W2582946978 @default.
• W2999596312 hasRelatedWork W2615522212 @default.
• W2999596312 hasRelatedWork W2619219755 @default.
• W2999596312 hasRelatedWork W2753012705 @default.
• W2999596312 hasRelatedWork W2790850591 @default.
• W2999596312 hasRelatedWork W2808421695 @default.
• W2999596312 hasRelatedWork W2944387176 @default.
• W2999596312 hasRelatedWork W2953713676 @default.
• W2999596312 hasRelatedWork W2962944041 @default.
• W2999596312 hasRelatedWork W2986185262 @default.
• W2999596312 hasRelatedWork W3006416029 @default.
• W2999596312 hasRelatedWork W3026133783 @default.
• W2999596312 hasRelatedWork W3036054814 @default.
• W2999596312 hasRelatedWork W3048777374 @default.
• W2999596312 hasRelatedWork W3083860260 @default.
• W2999596312 hasRelatedWork W3125245937 @default.
• W2999596312 hasRelatedWork W3185109031 @default.
• W2999596312 hasRelatedWork W3203844438 @default.
• W2999596312 hasRelatedWork W3209208698 @default.
• W2999596312 hasRelatedWork W925393145 @default.
• W2999596312 isParatext "false" @default.
• W2999596312 isRetracted "false" @default.

• next