{"total":15,"rows":[{"id":"2103.09568","title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","created":"2021-03-17","cited_by_count":256,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2107.03178","title":"Levels of explainable artificial intelligence for human-aligned conversational explanations","created":"2021-07-07","cited_by_count":21,"area":null},{"id":"2302.01680","title":"Two-Stage Constrained Actor-Critic for Short Video Recommendation","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2412.01566","title":"Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art","created":"2024-12-02","cited_by_count":6,"area":null},{"id":"2310.02360","title":"Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2204.06407","title":"Flexible Multiple-Objective Reinforcement Learning for Chip Placement","created":"2022-04-13","cited_by_count":3,"area":null},{"id":"2203.04579","title":"Multi-Objective reward generalization: Improving performance of Deep Reinforcement Learning for applications in single-asset trading","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2205.13248","title":"Constrained Reinforcement Learning for Short Video Recommendation","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2205.14834","title":"GraMeR: Graph Meta Reinforcement Learning for Multi-Objective Influence Maximization","created":"2022-05-30","cited_by_count":2,"area":null},{"id":"2110.06742","title":"A Review of the Deep Sea Treasure problem as a Multi-Objective Reinforcement Learning Benchmark","created":"2021-10-13","cited_by_count":1,"area":null},{"id":"2204.04988","title":"gTLO: A Generalized and Non-linear Multi-Objective Deep Reinforcement Learning Approach","created":"2022-04-11","cited_by_count":1,"area":null},{"id":"2211.04813","title":"Deep W-Networks: Solving Multi-Objective Optimisation Problems With Deep Reinforcement Learning","created":"2022-11-09","cited_by_count":1,"area":null},{"id":"2211.12987","title":"Reinforcement Learning Agent Design and Optimization with Bandwidth Allocation Model","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2512.12048","title":"Context-Aware Agentic Power Resources Optimisation in EV using Smart2ChargeApp","created":"2025-12-12","cited_by_count":0,"area":null}],"next_cursor":null}