Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315589025> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4315589025 abstract "We consider the problem of cooperative exploration where multiple robots need to cooperatively explore an unknown region as fast as possible. Multi-agent reinforcement learning (MARL) has recently become a trending paradigm for solving this challenge. However, existing MARL-based methods adopt action-making steps as the metric for exploration efficiency by assuming all the agents are acting in a fully synchronous manner: i.e., every single agent produces an action simultaneously and every single action is executed instantaneously at each time step. Despite its mathematical simplicity, such a synchronous MARL formulation can be problematic for real-world robotic applications. It can be typical that different robots may take slightly different wall-clock times to accomplish an atomic action or even periodically get lost due to hardware issues. Simply waiting for every robot being ready for the next action can be particularly time-inefficient. Therefore, we propose an asynchronous MARL solution, Asynchronous Coordination Explorer (ACE), to tackle this real-world challenge. We first extend a classical MARL algorithm, multi-agent PPO (MAPPO), to the asynchronous setting and additionally apply action-delay randomization to enforce the learned policy to generalize better to varying action delays in the real world. Moreover, each navigation agent is represented as a team-size-invariant CNN-based policy, which greatly benefits real-robot deployment by handling possible robot lost and allows bandwidth-efficient intra-agent communication through low-dimensional CNN features. We first validate our approach in a grid-based scenario. Both simulation and real-robot results show that ACE reduces over 10% actual exploration time compared with classical approaches. We also apply our framework to a high-fidelity visual-based environment, Habitat, achieving 28% improvement in exploration efficiency." @default.
- W4315589025 created "2023-01-11" @default.
- W4315589025 creator A5011500179 @default.
- W4315589025 creator A5023755254 @default.
- W4315589025 creator A5032903511 @default.
- W4315589025 creator A5033638005 @default.
- W4315589025 creator A5038635573 @default.
- W4315589025 creator A5044411292 @default.
- W4315589025 creator A5071845091 @default.
- W4315589025 creator A5072918003 @default.
- W4315589025 creator A5079594267 @default.
- W4315589025 creator A5079918191 @default.
- W4315589025 creator A5090856797 @default.
- W4315589025 date "2023-01-09" @default.
- W4315589025 modified "2023-10-18" @default.
- W4315589025 title "Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration" @default.
- W4315589025 doi "https://doi.org/10.48550/arxiv.2301.03398" @default.
- W4315589025 hasPublicationYear "2023" @default.
- W4315589025 type Work @default.
- W4315589025 citedByCount "0" @default.
- W4315589025 crossrefType "posted-content" @default.
- W4315589025 hasAuthorship W4315589025A5011500179 @default.
- W4315589025 hasAuthorship W4315589025A5023755254 @default.
- W4315589025 hasAuthorship W4315589025A5032903511 @default.
- W4315589025 hasAuthorship W4315589025A5033638005 @default.
- W4315589025 hasAuthorship W4315589025A5038635573 @default.
- W4315589025 hasAuthorship W4315589025A5044411292 @default.
- W4315589025 hasAuthorship W4315589025A5071845091 @default.
- W4315589025 hasAuthorship W4315589025A5072918003 @default.
- W4315589025 hasAuthorship W4315589025A5079594267 @default.
- W4315589025 hasAuthorship W4315589025A5079918191 @default.
- W4315589025 hasAuthorship W4315589025A5090856797 @default.
- W4315589025 hasBestOaLocation W43155890251 @default.
- W4315589025 hasConcept C120314980 @default.
- W4315589025 hasConcept C121332964 @default.
- W4315589025 hasConcept C151319957 @default.
- W4315589025 hasConcept C154945302 @default.
- W4315589025 hasConcept C2780791683 @default.
- W4315589025 hasConcept C31258907 @default.
- W4315589025 hasConcept C34413123 @default.
- W4315589025 hasConcept C41008148 @default.
- W4315589025 hasConcept C62520636 @default.
- W4315589025 hasConcept C90509273 @default.
- W4315589025 hasConcept C97541855 @default.
- W4315589025 hasConceptScore W4315589025C120314980 @default.
- W4315589025 hasConceptScore W4315589025C121332964 @default.
- W4315589025 hasConceptScore W4315589025C151319957 @default.
- W4315589025 hasConceptScore W4315589025C154945302 @default.
- W4315589025 hasConceptScore W4315589025C2780791683 @default.
- W4315589025 hasConceptScore W4315589025C31258907 @default.
- W4315589025 hasConceptScore W4315589025C34413123 @default.
- W4315589025 hasConceptScore W4315589025C41008148 @default.
- W4315589025 hasConceptScore W4315589025C62520636 @default.
- W4315589025 hasConceptScore W4315589025C90509273 @default.
- W4315589025 hasConceptScore W4315589025C97541855 @default.
- W4315589025 hasLocation W43155890251 @default.
- W4315589025 hasOpenAccess W4315589025 @default.
- W4315589025 hasPrimaryLocation W43155890251 @default.
- W4315589025 hasRelatedWork W1561560534 @default.
- W4315589025 hasRelatedWork W2002867377 @default.
- W4315589025 hasRelatedWork W2065963568 @default.
- W4315589025 hasRelatedWork W2089011450 @default.
- W4315589025 hasRelatedWork W2313989154 @default.
- W4315589025 hasRelatedWork W2364921833 @default.
- W4315589025 hasRelatedWork W2907045084 @default.
- W4315589025 hasRelatedWork W3119366040 @default.
- W4315589025 hasRelatedWork W3211352205 @default.
- W4315589025 hasRelatedWork W322005410 @default.
- W4315589025 isParatext "false" @default.
- W4315589025 isRetracted "false" @default.
- W4315589025 workType "article" @default.