{"total":983,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971,"area":"alignment"},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371,"area":null},{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290,"area":"wm"},{"id":"2505.15966","title":"Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning","created":"2025-05-21","cited_by_count":278,"area":"lr"},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2304.03279","title":"Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark","created":"2023-04-06","cited_by_count":182,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2010.13611","title":"OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning","created":"2020-10-26","cited_by_count":166,"area":"offlinerl"},{"id":"2106.08909","title":"Offline RL Without Off-Policy Evaluation","created":"2021-06-16","cited_by_count":151,"area":"offlinerl"},{"id":"2310.12567","title":"Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark","created":"2023-10-19","cited_by_count":143,"area":null},{"id":"2303.09824","title":"Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives","created":"2023-03-17","cited_by_count":114,"area":"driving"},{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112,"area":"offlinerl"},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"id":"2107.09003","title":"Constraints Penalized Q-learning for Safe Offline Reinforcement Learning","created":"2021-07-19","cited_by_count":91,"area":"offlinerl"},{"id":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91,"area":"diffusion"},{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80,"area":null},{"id":"2305.09304","title":"OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research","created":"2023-05-16","cited_by_count":80,"area":null},{"id":"2206.01079","title":"When does return-conditioned supervised learning work for offline reinforcement learning?","created":"2022-06-02","cited_by_count":76,"area":"offlinerl"},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71,"area":null},{"id":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71,"area":null},{"id":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69,"area":null},{"id":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69,"area":null},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2205.11814","title":"Penalized Proximal Policy Optimization for Safe Reinforcement Learning","created":"2022-05-24","cited_by_count":68,"area":null},{"id":"2202.07789","title":"Safe Reinforcement Learning by Imagining the Near Future","created":"2022-02-15","cited_by_count":67,"area":null},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64,"area":"offlinerl"},{"id":"2202.01741","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","created":"2022-02-03","cited_by_count":62,"area":"offlinerl"},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"area":null},{"id":"2205.07536","title":"Reachability Constrained Reinforcement Learning","created":"2022-05-16","cited_by_count":59,"area":null},{"id":"2303.06135","title":"Rewarding Chatbots for Real-World Engagement with Millions of Users","created":"2023-03-10","cited_by_count":59,"area":"alignment"},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"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":"2209.07089","title":"Constrained Update Projection Approach to Safe Policy Optimization","created":"2022-09-15","cited_by_count":58,"area":null},{"id":"2110.13136","title":"What Would Jiminy Cricket Do? Towards Agents That Behave Morally","created":"2021-10-25","cited_by_count":57,"area":null},{"id":"2302.03122","title":"State-wise Safe Reinforcement Learning: A Survey","created":"2023-02-06","cited_by_count":55,"area":null},{"id":"2202.04628","title":"Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration","created":"2022-02-09","cited_by_count":54,"area":null},{"id":"2307.07176","title":"SafeDreamer: Safe Reinforcement Learning with World Models","created":"2023-07-14","cited_by_count":54,"area":"wm"},{"id":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50,"area":null},{"id":"2109.06332","title":"Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2202.10341","title":"Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization","created":"2022-02-17","cited_by_count":49,"area":"driving"},{"id":"2106.09110","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","created":"2021-06-16","cited_by_count":47,"area":null},{"id":"2308.12517","title":"Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion","created":"2023-08-24","cited_by_count":47,"area":null},{"id":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"id":"2302.11312","title":"Behavior Proximal Policy Optimization","created":"2023-02-22","cited_by_count":43,"area":"offlinerl"},{"id":"2103.05134","title":"Constrained Learning with Non-Convex Losses","created":"2021-03-08","cited_by_count":42,"area":null},{"id":"2303.03226","title":"Safe Reinforcement Learning via Probabilistic Logic Shields","created":"2023-03-06","cited_by_count":42,"area":null},{"id":"2102.11941","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards","created":"2021-02-23","cited_by_count":40,"area":null},{"id":"2111.00072","title":"Generalized Proximal Policy Optimization with Sample Reuse","created":"2021-10-29","cited_by_count":40,"area":null},{"id":"2108.01846","title":"Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations","created":"2021-08-04","cited_by_count":39,"area":null},{"id":"2110.14770","title":"TRAIL: Near-Optimal Imitation Learning with Suboptimal Data","created":"2021-10-27","cited_by_count":39,"area":"offlinerl"},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2206.06270","title":"Near-Optimal Sample Complexity Bounds for Constrained MDPs","created":"2022-06-13","cited_by_count":37,"area":null},{"id":"2309.13528","title":"Iterative Reachability Estimation for Safe Reinforcement Learning","created":"2023-09-24","cited_by_count":37,"area":null},{"id":"2602.04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","created":"2026-02-04","cited_by_count":37,"area":"lr"},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2106.06239","title":"Safe Reinforcement Learning with Linear Function Approximation","created":"2021-06-11","cited_by_count":35,"area":null},{"id":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","cited_by_count":35,"area":null},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35,"area":null},{"id":"2203.02638","title":"Safe Reinforcement Learning for Legged Locomotion","created":"2022-03-05","cited_by_count":35,"area":null},{"id":"2105.12272","title":"Provable Representation Learning for Imitation with Contrastive Fourier Features","created":"2021-05-26","cited_by_count":34,"area":"offlinerl"},{"id":"2110.08923","title":"A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization","created":"2021-10-17","cited_by_count":34,"area":null},{"id":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"area":null},{"id":"2101.00531","title":"Context-Aware Safe Reinforcement Learning for Non-Stationary Environments","created":"2021-01-02","cited_by_count":33,"area":null},{"id":"2205.13536","title":"Verifying Learning-Based Robotic Navigation Systems","created":"2022-05-26","cited_by_count":33,"area":null},{"id":"2405.17713","title":"AI Alignment with Changing and Influenceable Reward Functions","created":"2024-05-28","cited_by_count":33,"area":"alignment"},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2103.01556","title":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","created":"2021-03-02","cited_by_count":32,"area":null},{"id":"2205.01975","title":"Aligning to Social Norms and Values in Interactive Narratives","created":"2022-05-04","cited_by_count":32,"area":null},{"id":"2401.03160","title":"HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving","created":"2024-01-06","cited_by_count":32,"area":"driving"},{"id":"2105.08881","title":"Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization","created":"2021-05-19","cited_by_count":31,"area":null},{"id":"2110.06831","title":"Safe Driving via Expert Guided Policy Optimization","created":"2021-10-13","cited_by_count":31,"area":"driving"},{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31,"area":null},{"id":"2305.18901","title":"Policy Optimization for Continuous Reinforcement Learning","created":"2023-05-30","cited_by_count":31,"area":null},{"id":"2105.10682","title":"Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety","created":"2021-05-22","cited_by_count":30,"area":null},{"id":"2106.07329","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","created":"2021-06-14","cited_by_count":30,"area":null},{"id":"2201.12427","title":"Towards Safe Reinforcement Learning with a Safety Editor Policy","created":"2022-01-28","cited_by_count":30,"area":null},{"id":"2202.01511","title":"Challenging Common Assumptions in Convex Reinforcement Learning","created":"2022-02-03","cited_by_count":30,"area":"offlinerl"},{"id":"2205.15043","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","created":"2022-05-30","cited_by_count":30,"area":null},{"id":"2503.00897","title":"A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning","created":"2025-03-02","cited_by_count":30,"area":"diffusion"},{"id":"2204.08125","title":"FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence","created":"2022-04-18","cited_by_count":29,"area":null},{"id":"2210.07573","title":"Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm","created":"2022-10-14","cited_by_count":29,"area":null},{"id":"2506.23844","title":"A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents","created":"2025-06-30","cited_by_count":29,"area":"agents"},{"id":"2110.07395","title":"Offline Reinforcement Learning with Soft Behavior Regularization","created":"2021-10-14","cited_by_count":28,"area":"offlinerl"},{"id":"2202.06626","title":"MuZero with Self-competition for Rate Control in VP9 Video Compression","created":"2022-02-14","cited_by_count":28,"area":null},{"id":"2306.00603","title":"Safe Offline Reinforcement Learning with Real-Time Budget Constraints","created":"2023-06-01","cited_by_count":28,"area":"offlinerl"},{"id":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28,"area":null},{"id":"2310.03225","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2105.13281","title":"GoSafe: Globally Optimal Safe Robot Learning","created":"2021-05-27","cited_by_count":27,"area":null},{"id":"2111.07695","title":"Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning","created":"2021-11-15","cited_by_count":27,"area":null},{"id":"2202.07152","title":"L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning","created":"2022-02-15","cited_by_count":27,"area":null},{"id":"2206.02346","title":"Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2105.14937","title":"Safe Pontryagin Differentiable Programming","created":"2021-05-31","cited_by_count":26,"area":null},{"id":"2106.11022","title":"Hard Choices in Artificial Intelligence","created":"2021-06-10","cited_by_count":26,"area":null},{"id":"2204.07417","title":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","created":"2022-04-15","cited_by_count":26,"area":null},{"id":"2210.10691","title":"Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes","created":"2022-10-19","cited_by_count":26,"area":null},{"id":"2502.02133","title":"Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification","created":"2025-02-04","cited_by_count":26,"area":"deeprl"}],"next_cursor":"100"}