Matches in SemOpenAlex for { <https://semopenalex.org/work/W3010176498> ?p ?o ?g. }
- W3010176498 abstract "Model Predictive Control (MPC) is a powerful control technique that handles constraints, takes the system's dynamics into account, and optimizes for a given cost function. In practice, however, it often requires an expert to craft and tune this cost function and find trade-offs between different state penalties to satisfy simple high level objectives. In this paper, we use Reinforcement Learning and in particular value learning to approximate the value function given only high level objectives, which can be sparse and binary. Building upon previous works, we present improvements that allowed us to successfully deploy the method on a real world unmanned ground vehicle. Our experiments show that our method can learn the cost function from scratch and without human intervention, while reaching a performance level similar to that of an expert-tuned MPC. We perform a quantitative comparison of these methods with standard MPC approaches both in simulation and on the real robot." @default.
- W3010176498 created "2020-03-13" @default.
- W3010176498 creator A5011023402 @default.
- W3010176498 creator A5028267080 @default.
- W3010176498 creator A5029156304 @default.
- W3010176498 creator A5046670804 @default.
- W3010176498 date "2020-03-06" @default.
- W3010176498 modified "2023-09-23" @default.
- W3010176498 title "Practical Reinforcement Learning For MPC: Learning from sparse objectives in under an hour on a real robot" @default.
- W3010176498 cites W1704276703 @default.
- W3010176498 cites W1983864916 @default.
- W3010176498 cites W1991700598 @default.
- W3010176498 cites W2010315317 @default.
- W3010176498 cites W2013610941 @default.
- W3010176498 cites W2027701333 @default.
- W3010176498 cites W2042795879 @default.
- W3010176498 cites W2061562262 @default.
- W3010176498 cites W2087070363 @default.
- W3010176498 cites W2104733512 @default.
- W3010176498 cites W2115955659 @default.
- W3010176498 cites W2121523122 @default.
- W3010176498 cites W2121863487 @default.
- W3010176498 cites W2165150801 @default.
- W3010176498 cites W2173248099 @default.
- W3010176498 cites W2257979135 @default.
- W3010176498 cites W2295431040 @default.
- W3010176498 cites W2584986912 @default.
- W3010176498 cites W2604382266 @default.
- W3010176498 cites W2618318883 @default.
- W3010176498 cites W2736601468 @default.
- W3010176498 cites W2892521964 @default.
- W3010176498 cites W2930426397 @default.
- W3010176498 cites W2943945102 @default.
- W3010176498 cites W2954115742 @default.
- W3010176498 cites W2963355572 @default.
- W3010176498 cites W2963960193 @default.
- W3010176498 cites W3030804074 @default.
- W3010176498 hasPublicationYear "2020" @default.
- W3010176498 type Work @default.
- W3010176498 sameAs 3010176498 @default.
- W3010176498 citedByCount "0" @default.
- W3010176498 crossrefType "posted-content" @default.
- W3010176498 hasAuthorship W3010176498A5011023402 @default.
- W3010176498 hasAuthorship W3010176498A5028267080 @default.
- W3010176498 hasAuthorship W3010176498A5029156304 @default.
- W3010176498 hasAuthorship W3010176498A5046670804 @default.
- W3010176498 hasConcept C111472728 @default.
- W3010176498 hasConcept C111919701 @default.
- W3010176498 hasConcept C119857082 @default.
- W3010176498 hasConcept C126255220 @default.
- W3010176498 hasConcept C138885662 @default.
- W3010176498 hasConcept C14036430 @default.
- W3010176498 hasConcept C14646407 @default.
- W3010176498 hasConcept C154945302 @default.
- W3010176498 hasConcept C172205157 @default.
- W3010176498 hasConcept C2775924081 @default.
- W3010176498 hasConcept C2780586882 @default.
- W3010176498 hasConcept C2781235140 @default.
- W3010176498 hasConcept C33923547 @default.
- W3010176498 hasConcept C41008148 @default.
- W3010176498 hasConcept C78458016 @default.
- W3010176498 hasConcept C86803240 @default.
- W3010176498 hasConcept C90509273 @default.
- W3010176498 hasConcept C97541855 @default.
- W3010176498 hasConceptScore W3010176498C111472728 @default.
- W3010176498 hasConceptScore W3010176498C111919701 @default.
- W3010176498 hasConceptScore W3010176498C119857082 @default.
- W3010176498 hasConceptScore W3010176498C126255220 @default.
- W3010176498 hasConceptScore W3010176498C138885662 @default.
- W3010176498 hasConceptScore W3010176498C14036430 @default.
- W3010176498 hasConceptScore W3010176498C14646407 @default.
- W3010176498 hasConceptScore W3010176498C154945302 @default.
- W3010176498 hasConceptScore W3010176498C172205157 @default.
- W3010176498 hasConceptScore W3010176498C2775924081 @default.
- W3010176498 hasConceptScore W3010176498C2780586882 @default.
- W3010176498 hasConceptScore W3010176498C2781235140 @default.
- W3010176498 hasConceptScore W3010176498C33923547 @default.
- W3010176498 hasConceptScore W3010176498C41008148 @default.
- W3010176498 hasConceptScore W3010176498C78458016 @default.
- W3010176498 hasConceptScore W3010176498C86803240 @default.
- W3010176498 hasConceptScore W3010176498C90509273 @default.
- W3010176498 hasConceptScore W3010176498C97541855 @default.
- W3010176498 hasOpenAccess W3010176498 @default.
- W3010176498 hasRelatedWork W2527551115 @default.
- W3010176498 hasRelatedWork W2591655474 @default.
- W3010176498 hasRelatedWork W2618318883 @default.
- W3010176498 hasRelatedWork W2762483932 @default.
- W3010176498 hasRelatedWork W2913300107 @default.
- W3010176498 hasRelatedWork W2955872978 @default.
- W3010176498 hasRelatedWork W2963414638 @default.
- W3010176498 hasRelatedWork W2966481145 @default.
- W3010176498 hasRelatedWork W2966735560 @default.
- W3010176498 hasRelatedWork W2966961840 @default.
- W3010176498 hasRelatedWork W2995706821 @default.
- W3010176498 hasRelatedWork W3009331570 @default.
- W3010176498 hasRelatedWork W3035457745 @default.
- W3010176498 hasRelatedWork W30592968 @default.
- W3010176498 hasRelatedWork W3098476112 @default.
- W3010176498 hasRelatedWork W3138215672 @default.
- W3010176498 hasRelatedWork W3166693310 @default.