Matches in SemOpenAlex for { <https://semopenalex.org/work/W2948155757> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2948155757 abstract "We present a methodology to deploy the stochastic policy gradient method, using actor-critic techniques, when the optimal policy is approximated using a parametric optimization problem, allowing one to enforce safety via hard constraints. For continuous input spaces, imposing safety restrictions on the stochastic policy can make the sampling and evaluation of its density difficult. This paper proposes a computationally effective approach to solve that issue. We will focus on policy approximations based on robust Nonlinear Model Predictive Control (NMPC), where safety can be treated explicitly. For the sake of brevity, we will detail safe policies in the robust linear MPC context only. The extension to the nonlinear case is possible but more complex. We will additionally present a technique to maintain the system safety throughout the learning process in the context of robust linear MPC. This paper has a companion paper treating the deterministic policy gradient case." @default.
- W2948155757 created "2019-06-14" @default.
- W2948155757 creator A5049645185 @default.
- W2948155757 creator A5055621494 @default.
- W2948155757 date "2019-06-10" @default.
- W2948155757 modified "2023-09-27" @default.
- W2948155757 title "Towards Safe Reinforcement Learning Using NMPC and Policy Gradients: Part II - Deterministic Case." @default.
- W2948155757 cites W1515851193 @default.
- W2948155757 cites W1529558080 @default.
- W2948155757 cites W1845972764 @default.
- W2948155757 cites W1980032585 @default.
- W2948155757 cites W1989099984 @default.
- W2948155757 cites W2028678875 @default.
- W2948155757 cites W2095233962 @default.
- W2948155757 cites W2098432798 @default.
- W2948155757 cites W2153885307 @default.
- W2948155757 cites W2155027007 @default.
- W2948155757 cites W2164957979 @default.
- W2948155757 cites W2165150801 @default.
- W2948155757 cites W2169209873 @default.
- W2948155757 cites W2798766386 @default.
- W2948155757 cites W2930426397 @default.
- W2948155757 cites W3029645440 @default.
- W2948155757 cites W3097925195 @default.
- W2948155757 cites W3101262841 @default.
- W2948155757 hasPublicationYear "2019" @default.
- W2948155757 type Work @default.
- W2948155757 sameAs 2948155757 @default.
- W2948155757 citedByCount "1" @default.
- W2948155757 countsByYear W29481557572019 @default.
- W2948155757 crossrefType "posted-content" @default.
- W2948155757 hasAuthorship W2948155757A5049645185 @default.
- W2948155757 hasAuthorship W2948155757A5055621494 @default.
- W2948155757 hasConcept C105795698 @default.
- W2948155757 hasConcept C111919701 @default.
- W2948155757 hasConcept C117251300 @default.
- W2948155757 hasConcept C121332964 @default.
- W2948155757 hasConcept C126255220 @default.
- W2948155757 hasConcept C151730666 @default.
- W2948155757 hasConcept C154945302 @default.
- W2948155757 hasConcept C158622935 @default.
- W2948155757 hasConcept C172205157 @default.
- W2948155757 hasConcept C199360897 @default.
- W2948155757 hasConcept C2775924081 @default.
- W2948155757 hasConcept C2778029271 @default.
- W2948155757 hasConcept C2779343474 @default.
- W2948155757 hasConcept C33923547 @default.
- W2948155757 hasConcept C41008148 @default.
- W2948155757 hasConcept C62520636 @default.
- W2948155757 hasConcept C86803240 @default.
- W2948155757 hasConcept C97541855 @default.
- W2948155757 hasConcept C98045186 @default.
- W2948155757 hasConceptScore W2948155757C105795698 @default.
- W2948155757 hasConceptScore W2948155757C111919701 @default.
- W2948155757 hasConceptScore W2948155757C117251300 @default.
- W2948155757 hasConceptScore W2948155757C121332964 @default.
- W2948155757 hasConceptScore W2948155757C126255220 @default.
- W2948155757 hasConceptScore W2948155757C151730666 @default.
- W2948155757 hasConceptScore W2948155757C154945302 @default.
- W2948155757 hasConceptScore W2948155757C158622935 @default.
- W2948155757 hasConceptScore W2948155757C172205157 @default.
- W2948155757 hasConceptScore W2948155757C199360897 @default.
- W2948155757 hasConceptScore W2948155757C2775924081 @default.
- W2948155757 hasConceptScore W2948155757C2778029271 @default.
- W2948155757 hasConceptScore W2948155757C2779343474 @default.
- W2948155757 hasConceptScore W2948155757C33923547 @default.
- W2948155757 hasConceptScore W2948155757C41008148 @default.
- W2948155757 hasConceptScore W2948155757C62520636 @default.
- W2948155757 hasConceptScore W2948155757C86803240 @default.
- W2948155757 hasConceptScore W2948155757C97541855 @default.
- W2948155757 hasConceptScore W2948155757C98045186 @default.
- W2948155757 hasLocation W29481557571 @default.
- W2948155757 hasOpenAccess W2948155757 @default.
- W2948155757 hasPrimaryLocation W29481557571 @default.
- W2948155757 hasRelatedWork W1549664030 @default.
- W2948155757 hasRelatedWork W1664312491 @default.
- W2948155757 hasRelatedWork W1997477676 @default.
- W2948155757 hasRelatedWork W2026546200 @default.
- W2948155757 hasRelatedWork W2027968610 @default.
- W2948155757 hasRelatedWork W2093524643 @default.
- W2948155757 hasRelatedWork W2113576982 @default.
- W2948155757 hasRelatedWork W2118578357 @default.
- W2948155757 hasRelatedWork W2131947667 @default.
- W2948155757 hasRelatedWork W2618190745 @default.
- W2948155757 hasRelatedWork W2771800791 @default.
- W2948155757 hasRelatedWork W281810645 @default.
- W2948155757 hasRelatedWork W2934856058 @default.
- W2948155757 hasRelatedWork W2948446629 @default.
- W2948155757 hasRelatedWork W3101405277 @default.
- W2948155757 hasRelatedWork W3102309758 @default.
- W2948155757 hasRelatedWork W3122550046 @default.
- W2948155757 hasRelatedWork W3126698570 @default.
- W2948155757 hasRelatedWork W76429203 @default.
- W2948155757 hasRelatedWork W2127818589 @default.
- W2948155757 isParatext "false" @default.
- W2948155757 isRetracted "false" @default.
- W2948155757 magId "2948155757" @default.
- W2948155757 workType "article" @default.