Matches in SemOpenAlex for { <https://semopenalex.org/work/W3113207880> ?p ?o ?g. }
- W3113207880 abstract "Most of the existing deep reinforcement learning (RL) approaches for session-based recommendations either rely on costly online interactions with real users, or rely on potentially biased rule-based or data-driven user-behavior models for learning. In this work, we instead focus on learning recommendation policies in the pure batch or offline setting, i.e. learning policies solely from offline historical interaction logs or batch data generated from an unknown and sub-optimal behavior policy, without further access to data from the real-world or user-behavior models. We propose BCD4Rec: Batch-Constrained Distributional RL for Session-based Recommendations. BCD4Rec builds upon the recent advances in batch (offline) RL and distributional RL to learn from offline logs while dealing with the intrinsically stochastic nature of rewards from the users due to varied latent interest preferences (environments). We demonstrate that BCD4Rec significantly improves upon the behavior policy as well as strong RL and non-RL baselines in the batch setting in terms of standard performance metrics like Click Through Rates or Buy Rates. Other useful properties of BCD4Rec include: i. recommending items from the correct latent categories indicating better value estimates despite large action space (of the order of number of items), and ii. overcoming popularity bias in clicked or bought items typically present in the offline logs." @default.
- W3113207880 created "2020-12-21" @default.
- W3113207880 creator A5038397893 @default.
- W3113207880 creator A5060155700 @default.
- W3113207880 creator A5071894271 @default.
- W3113207880 creator A5077227952 @default.
- W3113207880 creator A5079868316 @default.
- W3113207880 date "2020-12-16" @default.
- W3113207880 modified "2023-09-27" @default.
- W3113207880 title "Batch-Constrained Distributional Reinforcement Learning for Session-based Recommendation." @default.
- W3113207880 cites W1547925194 @default.
- W3113207880 cites W1757796397 @default.
- W3113207880 cites W2013702324 @default.
- W3113207880 cites W2042996020 @default.
- W3113207880 cites W2046033161 @default.
- W3113207880 cites W2102288976 @default.
- W3113207880 cites W2121863487 @default.
- W3113207880 cites W2131571251 @default.
- W3113207880 cites W2138108551 @default.
- W3113207880 cites W2138909795 @default.
- W3113207880 cites W2141559645 @default.
- W3113207880 cites W2145339207 @default.
- W3113207880 cites W2155968351 @default.
- W3113207880 cites W2781763969 @default.
- W3113207880 cites W2787933113 @default.
- W3113207880 cites W2803308811 @default.
- W3113207880 cites W2809307135 @default.
- W3113207880 cites W2892888989 @default.
- W3113207880 cites W2946996695 @default.
- W3113207880 cites W2953831886 @default.
- W3113207880 cites W2953981431 @default.
- W3113207880 cites W2962694783 @default.
- W3113207880 cites W2963423916 @default.
- W3113207880 cites W2963704132 @default.
- W3113207880 cites W2963757175 @default.
- W3113207880 cites W2964157711 @default.
- W3113207880 cites W2964199361 @default.
- W3113207880 cites W2971262355 @default.
- W3113207880 cites W2972561734 @default.
- W3113207880 cites W2972577225 @default.
- W3113207880 cites W2979211489 @default.
- W3113207880 cites W2984869362 @default.
- W3113207880 cites W2990162188 @default.
- W3113207880 cites W2995056525 @default.
- W3113207880 cites W3022566517 @default.
- W3113207880 cites W3022972087 @default.
- W3113207880 cites W3025606523 @default.
- W3113207880 cites W3033324992 @default.
- W3113207880 cites W3033478119 @default.
- W3113207880 cites W3034607397 @default.
- W3113207880 cites W3037440645 @default.
- W3113207880 cites W3043057128 @default.
- W3113207880 cites W3101707147 @default.
- W3113207880 hasPublicationYear "2020" @default.
- W3113207880 type Work @default.
- W3113207880 sameAs 3113207880 @default.
- W3113207880 citedByCount "3" @default.
- W3113207880 countsByYear W31132078802021 @default.
- W3113207880 crossrefType "posted-content" @default.
- W3113207880 hasAuthorship W3113207880A5038397893 @default.
- W3113207880 hasAuthorship W3113207880A5060155700 @default.
- W3113207880 hasAuthorship W3113207880A5071894271 @default.
- W3113207880 hasAuthorship W3113207880A5077227952 @default.
- W3113207880 hasAuthorship W3113207880A5079868316 @default.
- W3113207880 hasConcept C111919701 @default.
- W3113207880 hasConcept C119857082 @default.
- W3113207880 hasConcept C136764020 @default.
- W3113207880 hasConcept C154945302 @default.
- W3113207880 hasConcept C15744967 @default.
- W3113207880 hasConcept C172658912 @default.
- W3113207880 hasConcept C199360897 @default.
- W3113207880 hasConcept C2779182362 @default.
- W3113207880 hasConcept C2780102126 @default.
- W3113207880 hasConcept C2780490138 @default.
- W3113207880 hasConcept C2780586970 @default.
- W3113207880 hasConcept C2986087404 @default.
- W3113207880 hasConcept C41008148 @default.
- W3113207880 hasConcept C557471498 @default.
- W3113207880 hasConcept C77805123 @default.
- W3113207880 hasConcept C97541855 @default.
- W3113207880 hasConceptScore W3113207880C111919701 @default.
- W3113207880 hasConceptScore W3113207880C119857082 @default.
- W3113207880 hasConceptScore W3113207880C136764020 @default.
- W3113207880 hasConceptScore W3113207880C154945302 @default.
- W3113207880 hasConceptScore W3113207880C15744967 @default.
- W3113207880 hasConceptScore W3113207880C172658912 @default.
- W3113207880 hasConceptScore W3113207880C199360897 @default.
- W3113207880 hasConceptScore W3113207880C2779182362 @default.
- W3113207880 hasConceptScore W3113207880C2780102126 @default.
- W3113207880 hasConceptScore W3113207880C2780490138 @default.
- W3113207880 hasConceptScore W3113207880C2780586970 @default.
- W3113207880 hasConceptScore W3113207880C2986087404 @default.
- W3113207880 hasConceptScore W3113207880C41008148 @default.
- W3113207880 hasConceptScore W3113207880C557471498 @default.
- W3113207880 hasConceptScore W3113207880C77805123 @default.
- W3113207880 hasConceptScore W3113207880C97541855 @default.
- W3113207880 hasLocation W31132078801 @default.
- W3113207880 hasOpenAccess W3113207880 @default.
- W3113207880 hasPrimaryLocation W31132078801 @default.
- W3113207880 hasRelatedWork W2741586059 @default.