{"total":77,"rows":[{"id":"2201.13259","title":"Trajectory balance: Improved credit assignment in GFlowNets","created":"2022-01-31","cited_by_count":251,"area":null},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174,"area":null},{"id":"2202.13903","title":"Bayesian Structure Learning with Generative Flow Networks","created":"2022-02-28","cited_by_count":153,"area":null},{"id":"2209.12782","title":"Learning GFlowNets from partial episodes for improved convergence and stability","created":"2022-09-26","cited_by_count":132,"area":null},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"area":null},{"id":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59,"area":null},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2101.08862","title":"Breaking the Deadly Triad with a Target Network","created":"2021-01-21","cited_by_count":47,"area":null},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2103.00445","title":"Ensemble Bootstrapping for Q-Learning","created":"2021-02-28","cited_by_count":31,"area":null},{"id":"2204.06815","title":"deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks","created":"2022-04-14","cited_by_count":28,"area":null},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2103.06469","title":"Generalizable Episodic Memory for Deep Reinforcement Learning","created":"2021-03-11","cited_by_count":23,"area":null},{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2104.06922","title":"Safe Continuous Control with Constrained Model-Based Policy Optimization","created":"2021-04-14","cited_by_count":17,"area":null},{"id":"2112.03257","title":"Functional Regularization for Reinforcement Learning via Learned Fourier Features","created":"2021-12-06","cited_by_count":17,"area":null},{"id":"2205.15460","title":"Critic Sequential Monte Carlo","created":"2022-05-30","cited_by_count":16,"area":null},{"id":"2211.11030","title":"Adversarial Cheap Talk","created":"2022-11-20","cited_by_count":16,"area":null},{"id":"2202.05195","title":"Uncovering Instabilities in Variational-Quantum Deep Q-Networks","created":"2022-02-10","cited_by_count":14,"area":null},{"id":"2210.07432","title":"Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations","created":"2022-10-14","cited_by_count":14,"area":null},{"id":"2310.10735","title":"Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2209.07670","title":"Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks","created":"2022-09-16","cited_by_count":13,"area":null},{"id":"2105.14127","title":"Risk-Aware Transfer in Reinforcement Learning using Successor Features","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2106.11779","title":"Emphatic Algorithms for Deep Reinforcement Learning","created":"2021-06-21","cited_by_count":12,"area":null},{"id":"2302.01470","title":"Learning to Optimize for Reinforcement Learning","created":"2023-02-03","cited_by_count":12,"area":null},{"id":"2205.14495","title":"Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges","created":"2022-05-28","cited_by_count":11,"area":null},{"id":"2203.11526","title":"Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks","created":"2022-03-22","cited_by_count":9,"area":null},{"id":"2306.11918","title":"Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2508.01957","title":"Stochastic Encodings for Active Feature Acquisition","created":"2025-08-03","cited_by_count":9,"area":null},{"id":"2106.15419","title":"Convergent and Efficient Deep Q Network Algorithm","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2306.07124","title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2507.20057","title":"What Can Grokking Teach Us About Learning Under Nonstationarity?","created":"2025-07-26","cited_by_count":8,"area":null},{"id":"2106.02613","title":"Bridging the Gap Between Target Networks and Functional Regularization","created":"2021-06-04","cited_by_count":7,"area":null},{"id":"2112.05848","title":"Faster Deep Reinforcement Learning with Slower Online Network","created":"2021-12-10","cited_by_count":7,"area":null},{"id":"2205.08464","title":"Robust Losses for Learning Value Functions","created":"2022-05-17","cited_by_count":7,"area":null},{"id":"2106.14993","title":"Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment","created":"2021-06-28","cited_by_count":6,"area":null},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2211.06407","title":"Control Transformer: Robot Navigation in Unknown Environments through PRM-Guided Return-Conditioned Sequence Modeling","created":"2022-11-11","cited_by_count":6,"area":null},{"id":"2305.18435","title":"Statistically Efficient Bayesian Sequential Experiment Design via Reinforcement Learning with Cross-Entropy Estimators","created":"2023-05-29","cited_by_count":6,"area":null},{"id":"2312.05397","title":"On the Performance of Temporal Difference Learning With Neural Networks","created":"2023-12-08","cited_by_count":6,"area":null},{"id":"2107.05405","title":"Learning Expected Emphatic Traces for Deep RL","created":"2021-07-12","cited_by_count":5,"area":null},{"id":"2210.03325","title":"Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2406.02213","title":"Random Policy Evaluation Uncovers Policies of Generative Flow Networks","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2109.14419","title":"On the Estimation Bias in Double Q-Learning","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2202.09699","title":"Selective Credit Assignment","created":"2022-02-20","cited_by_count":4,"area":null},{"id":"2111.01865","title":"Off-Policy Correction for Deep Deterministic Policy Gradient Algorithms via Batch Prioritized Experience Replay","created":"2021-11-02","cited_by_count":3,"area":null},{"id":"2201.06468","title":"Chaining Value Functions for Off-Policy Learning","created":"2022-01-17","cited_by_count":3,"area":null},{"id":"2202.11512","title":"Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogistics","created":"2022-02-23","cited_by_count":3,"area":null},{"id":"2301.04299","title":"SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning","created":"2023-01-11","cited_by_count":3,"area":null},{"id":"2309.16819","title":"Multi-Bellman operator for convergence of $Q$-learning with linear function approximation","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2110.06906","title":"PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method","created":"2021-10-13","cited_by_count":2,"area":null},{"id":"2111.04845","title":"Hybrid BYOL-ViT: Efficient approach to deal with small datasets","created":"2021-11-08","cited_by_count":2,"area":null},{"id":"2111.06780","title":"AWD3: Dynamic Reduction of the Estimation Bias","created":"2021-11-12","cited_by_count":1,"area":null},{"id":"2111.11758","title":"The Impact of Data Distribution on Q-learning with Function Approximation","created":"2021-11-23","cited_by_count":1,"area":null},{"id":"2201.08610","title":"Deep Q-learning: a robust control approach","created":"2022-01-21","cited_by_count":1,"area":null},{"id":"2302.00533","title":"Distillation Policy Optimization","created":"2023-02-01","cited_by_count":1,"area":null},{"id":"2305.03196","title":"Emulation Learning for Neuromimetic Systems","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2312.05787","title":"Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization","created":"2023-12-10","cited_by_count":1,"area":null},{"id":"2509.15927","title":"Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2604.06938","title":"POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2606.29526","title":"The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2110.12081","title":"Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction","created":"2021-10-22","cited_by_count":0,"area":null},{"id":"2111.10103","title":"Uncertainty-aware Low-Rank Q-Matrix Estimation for Deep Reinforcement Learning","created":"2021-11-19","cited_by_count":0,"area":null},{"id":"2210.05262","title":"Factors of Influence of the Overestimation Bias of Q-Learning","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2210.12282","title":"Bridging the Gap Between Target Networks and Functional Regularization","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2212.05377","title":"Generalization Through the Lens of Learning Dynamics","created":"2022-12-11","cited_by_count":0,"area":null},{"id":"2212.10705","title":"Control of Continuous Quantum Systems with Many Degrees of Freedom based on Convergent Reinforcement Learning","created":"2022-12-21","cited_by_count":0,"area":null},{"id":"2303.00356","title":"A Deep Reinforcement Learning Trader without Offline Training","created":"2023-03-01","cited_by_count":0,"area":null},{"id":"2307.04841","title":"Loss Dynamics of Temporal Difference Reinforcement Learning","created":"2023-07-10","cited_by_count":0,"area":null},{"id":"2401.00330","title":"Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions","created":"2023-12-30","cited_by_count":0,"area":null},{"id":"2410.01643","title":"Stable Offline Value Function Learning with Bisimulation-based Representations","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2511.04666","title":"Forgetting is Everywhere","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2607.19397","title":"Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2610.09141","title":"A Cognitive-Aware QML-CRL Framework for Detecting Affinity and Romance-Investment Fraud","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}