FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089424104> ?p ?o ?g. }

• W3089424104 abstract "A common approach for defining a reward function for multi-objective reinforcement learning (MORL) problems is the weighted sum of the multiple objectives. The weights are then treated as design parameters dependent on the expertise (and preference) of the person performing the learning, with the typical result that a new solution is required for any change in these settings. This paper investigates the relationship between the reward function and the optimal value function for MORL; specifically addressing the question of how to approximate the optimal value function well beyond the set of weights for which the optimization problem was actually solved, thereby avoiding the need to recompute for any particular choice. We prove that the value function transforms smoothly given a transformation of weights of the reward function (and thus a smooth interpolation in the policy space). A Gaussian process is used to obtain a smooth interpolation over the reward function weights of the optimal value function for three well-known examples: Gridworld, Objectworld and Pendulum. The results show that the interpolation can provide robust values for sample states and actions in both discrete and continuous domain problems. Significant advantages arise from utilizing this interpolation technique in the domain of autonomous vehicles: easy, instant adaptation of user preferences while driving and true randomization of obstacle vehicle behavior preferences during training." @default.
• W3089424104 created "2020-10-08" @default.
• W3089424104 creator A5011665886 @default.
• W3089424104 creator A5032965719 @default.
• W3089424104 date "2020-05-01" @default.
• W3089424104 modified "2023-09-25" @default.
• W3089424104 title "Predicting optimal value functions by interpolating reward functions in scalarized multi-objective reinforcement learning" @default.
• W3089424104 cites W1502922572 @default.
• W3089424104 cites W194786220 @default.
• W3089424104 cites W2058192020 @default.
• W3089424104 cites W2076337359 @default.
• W3089424104 cites W2101234009 @default.
• W3089424104 cites W2117675763 @default.
• W3089424104 cites W2121863487 @default.
• W3089424104 cites W2141481921 @default.
• W3089424104 cites W2145339207 @default.
• W3089424104 cites W2145756561 @default.
• W3089424104 cites W2155027007 @default.
• W3089424104 cites W2156174663 @default.
• W3089424104 cites W2161767008 @default.
• W3089424104 cites W2182124586 @default.
• W3089424104 cites W2186820913 @default.
• W3089424104 cites W2540189295 @default.
• W3089424104 cites W2625366419 @default.
• W3089424104 cites W3103262232 @default.
• W3089424104 cites W1590206506 @default.
• W3089424104 doi "https://doi.org/10.1109/icra40945.2020.9197456" @default.
• W3089424104 hasPublicationYear "2020" @default.
• W3089424104 type Work @default.
• W3089424104 sameAs 3089424104 @default.
• W3089424104 citedByCount "1" @default.
• W3089424104 countsByYear W30894241042021 @default.
• W3089424104 crossrefType "proceedings-article" @default.
• W3089424104 hasAuthorship W3089424104A5011665886 @default.
• W3089424104 hasAuthorship W3089424104A5032965719 @default.
• W3089424104 hasBestOaLocation W30894241042 @default.
• W3089424104 hasConcept C104114177 @default.
• W3089424104 hasConcept C119857082 @default.
• W3089424104 hasConcept C121332964 @default.
• W3089424104 hasConcept C126255220 @default.
• W3089424104 hasConcept C134306372 @default.
• W3089424104 hasConcept C137800194 @default.
• W3089424104 hasConcept C14036430 @default.
• W3089424104 hasConcept C14646407 @default.
• W3089424104 hasConcept C154945302 @default.
• W3089424104 hasConcept C158622935 @default.
• W3089424104 hasConcept C163716315 @default.
• W3089424104 hasConcept C177264268 @default.
• W3089424104 hasConcept C192921069 @default.
• W3089424104 hasConcept C199360897 @default.
• W3089424104 hasConcept C2776291640 @default.
• W3089424104 hasConcept C33923547 @default.
• W3089424104 hasConcept C36503486 @default.
• W3089424104 hasConcept C41008148 @default.
• W3089424104 hasConcept C50644808 @default.
• W3089424104 hasConcept C61326573 @default.
• W3089424104 hasConcept C62520636 @default.
• W3089424104 hasConcept C78458016 @default.
• W3089424104 hasConcept C86803240 @default.
• W3089424104 hasConcept C91873725 @default.
• W3089424104 hasConcept C97541855 @default.
• W3089424104 hasConceptScore W3089424104C104114177 @default.
• W3089424104 hasConceptScore W3089424104C119857082 @default.
• W3089424104 hasConceptScore W3089424104C121332964 @default.
• W3089424104 hasConceptScore W3089424104C126255220 @default.
• W3089424104 hasConceptScore W3089424104C134306372 @default.
• W3089424104 hasConceptScore W3089424104C137800194 @default.
• W3089424104 hasConceptScore W3089424104C14036430 @default.
• W3089424104 hasConceptScore W3089424104C14646407 @default.
• W3089424104 hasConceptScore W3089424104C154945302 @default.
• W3089424104 hasConceptScore W3089424104C158622935 @default.
• W3089424104 hasConceptScore W3089424104C163716315 @default.
• W3089424104 hasConceptScore W3089424104C177264268 @default.
• W3089424104 hasConceptScore W3089424104C192921069 @default.
• W3089424104 hasConceptScore W3089424104C199360897 @default.
• W3089424104 hasConceptScore W3089424104C2776291640 @default.
• W3089424104 hasConceptScore W3089424104C33923547 @default.
• W3089424104 hasConceptScore W3089424104C36503486 @default.
• W3089424104 hasConceptScore W3089424104C41008148 @default.
• W3089424104 hasConceptScore W3089424104C50644808 @default.
• W3089424104 hasConceptScore W3089424104C61326573 @default.
• W3089424104 hasConceptScore W3089424104C62520636 @default.
• W3089424104 hasConceptScore W3089424104C78458016 @default.
• W3089424104 hasConceptScore W3089424104C86803240 @default.
• W3089424104 hasConceptScore W3089424104C91873725 @default.
• W3089424104 hasConceptScore W3089424104C97541855 @default.
• W3089424104 hasLocation W30894241041 @default.
• W3089424104 hasLocation W30894241042 @default.
• W3089424104 hasLocation W30894241043 @default.
• W3089424104 hasLocation W30894241044 @default.
• W3089424104 hasOpenAccess W3089424104 @default.
• W3089424104 hasPrimaryLocation W30894241041 @default.
• W3089424104 hasRelatedWork W10913952 @default.
• W3089424104 hasRelatedWork W11181584 @default.
• W3089424104 hasRelatedWork W1268192 @default.
• W3089424104 hasRelatedWork W1279312 @default.
• W3089424104 hasRelatedWork W1493653 @default.
• W3089424104 hasRelatedWork W4551202 @default.
• W3089424104 hasRelatedWork W5779190 @default.
• W3089424104 hasRelatedWork W6083205 @default.

• next