{"list":"other","total":57,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2504.20571","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","created":"2025-04-29","cited_by_count":295},{"id":"1904.12901","title":"Challenges of Real-World Reinforcement Learning","created":"2019-04-29","cited_by_count":291},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"1704.02532","title":"Deep Reinforcement Learning framework for Autonomous Driving","created":"2017-04-08","cited_by_count":225},{"id":"2012.15761","title":"Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection","created":"2020-12-31","cited_by_count":221},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"1711.00138","title":"Visualizing and Understanding Atari Agents","created":"2017-10-31","cited_by_count":141},{"id":"2502.11886","title":"LIMR: Less is More for RL Scaling","created":"2025-02-17","cited_by_count":139},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135},{"id":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104},{"id":"2504.05520","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","created":"2025-04-07","cited_by_count":93},{"id":"2504.13818","title":"Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning","created":"2025-04-18","cited_by_count":84},{"id":"1906.02500","title":"Towards Interpretable Reinforcement Learning Using Attention Augmented Agents","created":"2019-06-06","cited_by_count":82},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81},{"id":"1602.02658","title":"Graying the black box: Understanding DQNs","created":"2016-02-08","cited_by_count":68},{"id":"1906.08473","title":"Data Cleansing for Models Trained with SGD","created":"2019-06-20","cited_by_count":67},{"id":"2402.10500","title":"Active Preference Optimization for Sample Efficient RLHF","created":"2024-02-16","cited_by_count":62},{"id":"1912.05743","title":"Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning","created":"2019-12-09","cited_by_count":60},{"id":"2402.08114","title":"Active Preference Learning for Large Language Models","created":"2024-02-12","cited_by_count":58},{"id":"1912.12191","title":"Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution","created":"2019-12-23","cited_by_count":50},{"id":"2311.00500","title":"Intriguing Properties of Data Attribution on Diffusion Models","created":"2023-11-01","cited_by_count":47},{"id":"2306.09345","title":"Evaluating Data Attribution for Text-to-Image Models","created":"2023-06-15","cited_by_count":45},{"id":"2410.17413","title":"Scalable Influence and Fact Tracing for Large Language Model Pretraining","created":"2024-10-22","cited_by_count":42},{"id":"1809.06061","title":"Transparency and Explanation in Deep Reinforcement Learning Neural Networks","created":"2018-09-17","cited_by_count":40},{"id":"2412.09538","title":"Capturing the Temporal Dependence of Training Data Influence","created":"2024-12-12","cited_by_count":35},{"id":"2409.18153","title":"Most Influential Subset Selection: Challenges, Promises, and Beyond","created":"2024-09-25","cited_by_count":32},{"id":"2102.13045","title":"Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods","created":"2021-02-25","cited_by_count":31},{"id":"2306.17833","title":"Resetting the Optimizer in Deep RL: An Empirical Study","created":"2023-06-30","cited_by_count":26},{"id":"2405.11724","title":"Token-wise Influential Training Data Retrieval for Large Language Models","created":"2024-05-20","cited_by_count":20},{"id":"2410.01280","title":"Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models","created":"2024-10-02","cited_by_count":15},{"id":"2401.09031","title":"Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation","created":"2024-01-17","cited_by_count":14},{"id":"2201.05759","title":"FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes","created":"2022-01-15","cited_by_count":12},{"id":"2502.06869","title":"A Survey on Explainable Deep Reinforcement Learning","created":"2025-02-08","cited_by_count":12},{"id":"2308.07795","title":"Learning to Identify Critical States for Reinforcement Learning from Videos","created":"2023-08-15","cited_by_count":9},{"id":"2502.04354","title":"Reviving The Classics: Active Reward Modeling in Large Language Model Alignment","created":"2025-02-04","cited_by_count":8},{"id":"2305.04073","title":"Explaining RL Decisions with Trajectories","created":"2023-05-06","cited_by_count":7},{"id":"2405.03064","title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation","created":"2024-05-05","cited_by_count":7},{"id":"2503.14973","title":"Behaviour Discovery and Attribution for Explainable Reinforcement Learning","created":"2025-03-19","cited_by_count":2}],"next_cursor":null}