{"total":34,"rows":[{"id":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2204.11966","title":"Estimating and Penalizing Induced Preference Shifts in Recommender Systems","created":"2022-04-25","cited_by_count":29,"area":null},{"id":"2109.04083","title":"User Tampering in Reinforcement Learning Recommender Systems","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2103.08057","title":"RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems","created":"2021-03-14","cited_by_count":21,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2111.06978","title":"RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN","created":"2021-11-12","cited_by_count":15,"area":null},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2110.07554","title":"Looper: An end-to-end ML platform for product decisions","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2211.14673","title":"Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex","created":"2022-11-26","cited_by_count":8,"area":null},{"id":"2309.06375","title":"Modeling Recommender Ecosystems: Research Challenges at the Intersection of Mechanism Design, Reinforcement Learning and Generative Models","created":"2023-09-08","cited_by_count":7,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2110.11073","title":"RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2202.10381","title":"Rule Mining over Knowledge Graphs via Reinforcement Learning","created":"2022-02-21","cited_by_count":5,"area":null},{"id":"2206.11338","title":"Synthetic Data-Based Simulators for Recommender Systems: A Survey","created":"2022-06-22","cited_by_count":5,"area":null},{"id":"2312.14095","title":"RetailSynth: Synthetic Data Generation for Retail AI Systems Evaluation","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2110.10655","title":"Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning","created":"2021-10-20","cited_by_count":3,"area":null},{"id":"2312.15313","title":"Human-Centric Resource Allocation for the Metaverse With Multiaccess Edge Computing","created":"2023-12-23","cited_by_count":3,"area":null},{"id":"2103.14407","title":"Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow","created":"2021-03-26","cited_by_count":2,"area":null},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2107.06686","title":"Safer Reinforcement Learning through Transferable Instinct Networks","created":"2021-07-14","cited_by_count":1,"area":null},{"id":"2206.06878","title":"Temporal Multimodal Multivariate Learning","created":"2022-06-14","cited_by_count":1,"area":null},{"id":"2212.00906","title":"Karolos: An Open-Source Reinforcement Learning Framework for Robot-Task Environments","created":"2022-12-01","cited_by_count":1,"area":null},{"id":"2308.12445","title":"An Intentional Forgetting-Driven Self-Healing Method For Deep Reinforcement Learning Systems","created":"2023-08-23","cited_by_count":1,"area":null},{"id":"2409.20055","title":"Neural Click Models for Recommender Systems","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2103.05737","title":"The AI Arena: A Framework for Distributed Multi-Agent Reinforcement Learning","created":"2021-03-09","cited_by_count":0,"area":null},{"id":"2105.10587","title":"Techniques Toward Optimizing Viewability in RTB Ad Campaigns Using Reinforcement Learning","created":"2021-05-21","cited_by_count":0,"area":null},{"id":"2107.08383","title":"GuideBoot: Guided Bootstrap for Deep Contextual Bandits","created":"2021-07-18","cited_by_count":0,"area":null},{"id":"2112.05519","title":"A Validation Tool for Designing Reinforcement Learning Environments","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2304.13033","title":"SmartChoices: Augmenting Software with Learned Implementations","created":"2023-04-12","cited_by_count":0,"area":null},{"id":"2309.08622","title":"Representation Learning in Low-rank Slate-based Recommender Systems","created":"2023-09-10","cited_by_count":0,"area":null},{"id":"2404.00057","title":"PerOS: Personalized Self-Adapting Operating Systems in the Cloud","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2412.19372","title":"Minimal Batch Adaptive Learning Policy Engine for Real-Time Mid-Price Forecasting in High-Frequency Trading","created":"2024-12-26","cited_by_count":0,"area":null}],"next_cursor":null}