Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324301450> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4324301450 abstract "The synergies between Quality-Diversity (QD) and Deep Reinforcement Learning (RL) have led to powerful hybrid QD-RL algorithms that have shown tremendous potential, and brings the best of both fields. However, only a single deep RL algorithm (TD3) has been used in prior hybrid methods despite notable progress made by other RL algorithms. Additionally, there are fundamental differences in the optimization procedures between QD and RL which would benefit from a more principled approach. We propose Generalized Actor-Critic QD-RL, a unified modular framework for actor-critic deep RL methods in the QD-RL setting. This framework provides a path to study insights from Deep RL in the QD-RL setting, which is an important and efficient way to make progress in QD-RL. We introduce two new algorithms, PGA-ME (SAC) and PGA-ME (DroQ) which apply recent advancements in Deep RL to the QD-RL setting, and solves the humanoid environment which was not possible using existing QD-RL algorithms. However, we also find that not all insights from Deep RL can be effectively translated to QD-RL. Critically, this work also demonstrates that the actor-critic models in QD-RL are generally insufficiently trained and performance gains can be achieved without any additional environment evaluations." @default.
- W4324301450 created "2023-03-16" @default.
- W4324301450 creator A5011437628 @default.
- W4324301450 creator A5011747084 @default.
- W4324301450 creator A5060282741 @default.
- W4324301450 date "2023-03-10" @default.
- W4324301450 modified "2023-10-16" @default.
- W4324301450 title "Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning" @default.
- W4324301450 doi "https://doi.org/10.48550/arxiv.2303.06164" @default.
- W4324301450 hasPublicationYear "2023" @default.
- W4324301450 type Work @default.
- W4324301450 citedByCount "0" @default.
- W4324301450 crossrefType "posted-content" @default.
- W4324301450 hasAuthorship W4324301450A5011437628 @default.
- W4324301450 hasAuthorship W4324301450A5011747084 @default.
- W4324301450 hasAuthorship W4324301450A5060282741 @default.
- W4324301450 hasBestOaLocation W43243014501 @default.
- W4324301450 hasConcept C101468663 @default.
- W4324301450 hasConcept C108583219 @default.
- W4324301450 hasConcept C111472728 @default.
- W4324301450 hasConcept C111919701 @default.
- W4324301450 hasConcept C138885662 @default.
- W4324301450 hasConcept C154945302 @default.
- W4324301450 hasConcept C2779530757 @default.
- W4324301450 hasConcept C2984842247 @default.
- W4324301450 hasConcept C41008148 @default.
- W4324301450 hasConcept C97541855 @default.
- W4324301450 hasConceptScore W4324301450C101468663 @default.
- W4324301450 hasConceptScore W4324301450C108583219 @default.
- W4324301450 hasConceptScore W4324301450C111472728 @default.
- W4324301450 hasConceptScore W4324301450C111919701 @default.
- W4324301450 hasConceptScore W4324301450C138885662 @default.
- W4324301450 hasConceptScore W4324301450C154945302 @default.
- W4324301450 hasConceptScore W4324301450C2779530757 @default.
- W4324301450 hasConceptScore W4324301450C2984842247 @default.
- W4324301450 hasConceptScore W4324301450C41008148 @default.
- W4324301450 hasConceptScore W4324301450C97541855 @default.
- W4324301450 hasLocation W43243014501 @default.
- W4324301450 hasOpenAccess W4324301450 @default.
- W4324301450 hasPrimaryLocation W43243014501 @default.
- W4324301450 hasRelatedWork W2620920084 @default.
- W4324301450 hasRelatedWork W2950066684 @default.
- W4324301450 hasRelatedWork W3044383684 @default.
- W4324301450 hasRelatedWork W3124304076 @default.
- W4324301450 hasRelatedWork W3139644427 @default.
- W4324301450 hasRelatedWork W3211352205 @default.
- W4324301450 hasRelatedWork W4298388782 @default.
- W4324301450 hasRelatedWork W4299822940 @default.
- W4324301450 hasRelatedWork W4317552138 @default.
- W4324301450 hasRelatedWork W1829305295 @default.
- W4324301450 isParatext "false" @default.
- W4324301450 isRetracted "false" @default.
- W4324301450 workType "article" @default.