{"total":55,"rows":[{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2408.10215","title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","created":"2024-07-22","cited_by_count":38,"area":"deeprl"},{"id":"2305.16217","title":"Beyond Reward: Offline Preference-guided Policy Optimization","created":"2023-05-25","cited_by_count":35,"area":"alignment"},{"id":"2311.12495","title":"Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework","created":"2023-11-21","cited_by_count":31,"area":null},{"id":"2206.11326","title":"Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer","created":"2022-06-22","cited_by_count":22,"area":null},{"id":"2209.07133","title":"COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model Checking","created":"2022-09-15","cited_by_count":19,"area":null},{"id":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2407.00401","title":"PUZZLES: A Benchmark for Neural Algorithmic Reasoning","created":"2024-06-29","cited_by_count":13,"area":null},{"id":"2210.01801","title":"Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation","created":"2022-10-02","cited_by_count":11,"area":null},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2401.14811","title":"On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Tasks","created":"2024-01-26","cited_by_count":9,"area":"deeprl"},{"id":"2404.04920","title":"Regularized Conditional Diffusion Model for Multi-Task Preference Alignment","created":"2024-04-07","cited_by_count":9,"area":"diffusion"},{"id":"2409.10218","title":"Safety-Oriented Pruning and Interpretation of Reinforcement Learning Policies","created":"2024-09-16","cited_by_count":9,"area":"deeprl"},{"id":"2310.00435","title":"Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards","created":"2023-09-30","cited_by_count":8,"area":null},{"id":"2408.13493","title":"Thresholded Lexicographic Ordered Multiobjective Reinforcement Learning","created":"2024-08-24","cited_by_count":8,"area":"deeprl"},{"id":"2503.00799","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","created":"2025-03-02","cited_by_count":8,"area":"deeprl"},{"id":"2405.13022","title":"LLMs can learn self-restraint through iterative self-reflection","created":"2024-05-15","cited_by_count":6,"area":null},{"id":"2409.10188","title":"Enhancing RL Safety with Counterfactual LLM Reasoning","created":"2024-09-16","cited_by_count":6,"area":"lr"},{"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":"2211.13032","title":"Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2212.05337","title":"Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking","created":"2022-12-10","cited_by_count":5,"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":"2403.18725","title":"Probabilistic Model Checking of Stochastic Reinforcement Learning Policies","created":"2024-03-27","cited_by_count":5,"area":"deeprl"},{"id":"2407.16970","title":"Towards Aligning Language Models with Textual Feedback","created":"2024-07-24","cited_by_count":5,"area":"alignment"},{"id":"2305.19223","title":"Intent-aligned AI systems deplete human agency: the need for agency foundations research in AI safety","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2402.02665","title":"Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning","created":"2024-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2410.11221","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2505.02579","title":"EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning","created":"2025-05-05","cited_by_count":4,"area":null},{"id":"2207.00368","title":"Multi-Objective Coordination Graphs for the Expected Scalarised Returns with Generative Flow Models","created":"2022-07-01","cited_by_count":3,"area":null},{"id":"2401.16452","title":"Context-Former: Stitching via Latent Conditioned Sequence Modeling","created":"2024-01-29","cited_by_count":3,"area":"offlinerl"},{"id":"2501.03187","title":"Turn-based Multi-Agent Reinforcement Learning Model Checking","created":"2025-01-06","cited_by_count":3,"area":null},{"id":"2508.16581","title":"Increasing Interaction Fidelity: Training Routines for Biomechanical Models in HCI","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2602.04809","title":"Beyond Rewards in Reinforcement Learning for Cyber Defence","created":"2026-02-04","cited_by_count":3,"area":"deeprl"},{"id":"2602.14505","title":"Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC","created":"2026-02-16","cited_by_count":3,"area":"deeprl"},{"id":"2301.13812","title":"Learning Roles with Emergent Social Value Orientations","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2401.03163","title":"An Empirical Investigation of Value-Based Multi-objective Reinforcement Learning for Stochastic Environments","created":"2024-01-06","cited_by_count":2,"area":"deeprl"},{"id":"2501.03142","title":"Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies","created":"2025-01-06","cited_by_count":2,"area":"deeprl"},{"id":"2505.12049","title":"Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2410.00081","title":"From homeostasis to resource sharing: Biologically and economically aligned multi-objective multi-agent gridworld-based AI safety benchmarks","created":"2024-09-30","cited_by_count":1,"area":"agents"},{"id":"2410.05496","title":"Intuitions of Compromise: Utilitarianism vs. Contractualism","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2509.02655","title":"BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2511.18181","title":"MOMA-AC: A preference-driven actor-critic framework for continuous multi-objective multi-agent reinforcement learning","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2402.11653","title":"Combinatorial Client-Master Multiagent Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing","created":"2024-02-18","cited_by_count":0,"area":null},{"id":"2508.05165","title":"Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models","created":"2025-08-07","cited_by_count":0,"area":"alignment"},{"id":"2510.20408","title":"Balancing Specialization and Centralization: A Multi-Agent Reinforcement Learning Benchmark for Sequential Industrial Control","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2512.01502","title":"Formal Verification of Noisy Quantum Reinforcement Learning Policies","created":"2025-12-01","cited_by_count":0,"area":"deeprl"},{"id":"2602.06525","title":"Progress Constraints for Reinforcement Learning in Behavior Trees","created":"2026-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2603.02396","title":"COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Management","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.08412","title":"Aligning to Illusions: Choice Blindness in Human and AI Feedback","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2606.14693","title":"Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.21321","title":"Objective-Behavior Alignment: Diagnostics for MORL Policy Selection","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.29559","title":"LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback","created":"2026-07-31","cited_by_count":0,"area":"alignment"},{"id":"2608.25723","title":"It's a matter of timescale: non-linear utility in successor features and multi-objective planning and learning","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.01597","title":"The Rise of Verbal Reinforcement Learning","created":"2026-09-01","cited_by_count":0,"area":"alignment"}],"next_cursor":null}