{"total":100,"rows":[{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2302.05446","title":"Robust Scheduling with GFlowNets","created":"2023-01-17","cited_by_count":69,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2509.03493","title":"On Entropy Control in LLM-RL Algorithms","created":"2025-09-03","cited_by_count":40,"area":null},{"id":"2106.00285","title":"Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning","created":"2021-06-01","cited_by_count":38,"area":null},{"id":"2101.07012","title":"Regularized Policies are Reward Robust","created":"2021-01-18","cited_by_count":32,"area":null},{"id":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"area":null},{"id":"2310.20703","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","created":"2023-10-31","cited_by_count":27,"area":null},{"id":"2110.10117","title":"Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization","created":"2021-10-19","cited_by_count":25,"area":null},{"id":"2305.14502","title":"RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2211.16715","title":"Policy Optimization over General State and Action Spaces","created":"2022-11-30","cited_by_count":23,"area":null},{"id":"2203.12592","title":"Your Policy Regularizer is Secretly an Adversary","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2202.06618","title":"A Differential Entropy Estimator for Training Neural Networks","created":"2022-02-14","cited_by_count":20,"area":null},{"id":"2206.00833","title":"Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm","created":"2022-06-02","cited_by_count":20,"area":null},{"id":"2202.00308","title":"PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation","created":"2022-02-01","cited_by_count":17,"area":null},{"id":"2106.04096","title":"Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation","created":"2021-06-08","cited_by_count":16,"area":null},{"id":"2112.11921","title":"Variational Quantum Soft Actor-Critic","created":"2021-12-20","cited_by_count":15,"area":null},{"id":"2212.07536","title":"Robust Policy Optimization in Deep Reinforcement Learning","created":"2022-12-14","cited_by_count":15,"area":null},{"id":"2311.14168","title":"Fast Policy Learning for Linear Quadratic Control with Entropy Regularization","created":"2023-11-23","cited_by_count":13,"area":null},{"id":"2409.06290","title":"EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification","created":"2024-09-10","cited_by_count":13,"area":null},{"id":"2405.20250","title":"Entropy annealing for policy mirror descent in continuous time and space","created":"2024-05-30","cited_by_count":12,"area":null},{"id":"2104.11706","title":"Safe Chance Constrained Reinforcement Learning for Batch Process Control","created":"2021-04-23","cited_by_count":11,"area":null},{"id":"2309.14597","title":"Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control","created":"2023-09-26","cited_by_count":11,"area":null},{"id":"2102.06234","title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","created":"2021-02-11","cited_by_count":10,"area":null},{"id":"2112.11622","title":"An Alternate Policy Gradient Estimator for Softmax Policies","created":"2021-12-22","cited_by_count":9,"area":null},{"id":"2402.07808","title":"Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation","created":"2024-02-12","cited_by_count":9,"area":null},{"id":"2502.08208","title":"Exploring Exploration in Bayesian Optimization","created":"2025-02-12","cited_by_count":9,"area":null},{"id":"2510.18460","title":"Learning Boltzmann Generators via Constrained Mass Transport","created":"2025-10-21","cited_by_count":9,"area":null},{"id":"2110.01212","title":"Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence","created":"2021-10-04","cited_by_count":8,"area":null},{"id":"2111.02994","title":"Towards an Understanding of Default Policies in Multitask Policy Optimization","created":"2021-11-04","cited_by_count":8,"area":null},{"id":"2602.03392","title":"On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":8,"area":null},{"id":"2102.06042","title":"Modeling the Interaction between Agents in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-10","cited_by_count":7,"area":null},{"id":"2305.05586","title":"RLocator: Reinforcement Learning for Bug Localization","created":"2023-05-09","cited_by_count":7,"area":null},{"id":"2201.12434","title":"Do You Need the Entropy Reward (in Practice)?","created":"2022-01-28","cited_by_count":6,"area":null},{"id":"2204.09424","title":"SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2405.01616","title":"Generative Active Learning for the Search of Small-molecule Protein Binders","created":"2024-05-02","cited_by_count":6,"area":null},{"id":"2111.08172","title":"Off-Policy Actor-Critic with Emphatic Weightings","created":"2021-11-16","cited_by_count":5,"area":null},{"id":"2603.02155","title":"Near-Optimal Regret for KL-Regularized Multi-Armed Bandits","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2109.10883","title":"ENERO: Efficient Real-Time WAN Routing Optimization with Deep Reinforcement Learning","created":"2021-09-22","cited_by_count":4,"area":null},{"id":"2209.06259","title":"Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization","created":"2022-09-13","cited_by_count":4,"area":null},{"id":"2209.14513","title":"How Does Return Distribution in Distributional Reinforcement Learning Help Optimization?","created":"2022-09-29","cited_by_count":4,"area":null},{"id":"2301.12038","title":"STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning","created":"2023-01-28","cited_by_count":4,"area":null},{"id":"2305.06851","title":"Policy Gradient Algorithms Implicitly Optimize by Continuation","created":"2023-05-11","cited_by_count":4,"area":null},{"id":"2409.04744","title":"Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Framework","created":"2024-09-07","cited_by_count":4,"area":null},{"id":"2102.06808","title":"Planning and Learning Using Adaptive Entropy Tree Search","created":"2021-02-12","cited_by_count":3,"area":null},{"id":"2107.05217","title":"Cautious Actor-Critic","created":"2021-07-12","cited_by_count":3,"area":null},{"id":"2110.02398","title":"Approximate Newton policy gradient algorithms","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2112.00940","title":"Reward-Free Attacks in Multi-Agent Reinforcement Learning","created":"2021-12-02","cited_by_count":3,"area":null},{"id":"2210.14685","title":"Leveraging Demonstrations with Latent Space Priors","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2211.11869","title":"Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks","created":"2022-11-21","cited_by_count":3,"area":null},{"id":"2302.03364","title":"Population-size-Aware Policy Optimization for Mean-Field Games","created":"2023-02-07","cited_by_count":3,"area":null},{"id":"2303.14966","title":"Adaptive Federated Learning via New Entropy Approach","created":"2023-03-27","cited_by_count":3,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2201.05560","title":"Demystifying Reinforcement Learning in Time-Varying Systems","created":"2022-01-14","cited_by_count":2,"area":null},{"id":"2202.07496","title":"Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2202.10464","title":"A Globally Convergent Evolutionary Strategy for Stochastic Constrained Optimization with Applications to Reinforcement Learning","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2202.10506","title":"Accelerating Primal-dual Methods for Regularized Markov Decision Processes","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2303.12785","title":"Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality","created":"2023-03-22","cited_by_count":2,"area":null},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2512.23087","title":"Dynamic Vocabulary Pruning: Stable LLM-RL by Taming the Tail","created":"2025-12-28","cited_by_count":2,"area":null},{"id":"2605.11908","title":"Delightful Gradients Accelerate Corner Escape","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2102.03138","title":"An advantage actor-critic algorithm for robotic motion planning in dense and dynamic scenarios","created":"2021-02-05","cited_by_count":1,"area":null},{"id":"2102.07889","title":"Distributionally-Constrained Policy Optimization via Unbalanced Optimal Transport","created":"2021-02-15","cited_by_count":1,"area":null},{"id":"2106.13037","title":"Mix and Mask Actor-Critic Methods","created":"2021-06-24","cited_by_count":1,"area":null},{"id":"2107.07659","title":"Geometric Value Iteration: Dynamic Error-Aware KL Regularization for Reinforcement Learning","created":"2021-07-16","cited_by_count":1,"area":null},{"id":"2108.10533","title":"Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning","created":"2021-08-24","cited_by_count":1,"area":null},{"id":"2208.02369","title":"Deep VULMAN: A Deep Reinforcement Learning-Enabled Cyber Vulnerability Management Framework","created":"2022-08-03","cited_by_count":1,"area":null},{"id":"2208.11747","title":"Entropy Regularization for Population Estimation","created":"2022-08-24","cited_by_count":1,"area":null},{"id":"2208.13125","title":"Normality-Guided Distributional Reinforcement Learning for Continuous Control","created":"2022-08-28","cited_by_count":1,"area":null},{"id":"2302.10058","title":"Differentiable Arbitrating in Zero-sum Markov Games","created":"2023-02-20","cited_by_count":1,"area":null},{"id":"2310.11075","title":"Sim-to-Real Transfer of Adaptive Control Parameters for AUV Stabilization under Current Disturbance","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2404.00081","title":"Molecular Generative Adversarial Network with Multi-Property Optimization","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2505.17714","title":"PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2505.20579","title":"The challenge of hidden gifts in multi-agent reinforcement learning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2509.21765","title":"Lifelong Learning with Behavior Consolidation for Vehicle Routing","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2511.15002","title":"Task Specific Sharpness Aware O-RAN Resource Management using Multi Agent Reinforcement Learning","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2602.08965","title":"Learning to Coordinate via Quantum Entanglement in Multi-Agent Reinforcement Learning","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.15001","title":"How Log-Barrier Helps Exploration in Policy Optimization","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2101.01178","title":"Advances in Electron Microscopy with Deep Learning","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2107.05798","title":"Cautious Policy Programming: Exploiting KL Regularization in Monotonic Policy Improvement for Reinforcement Learning","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2205.07467","title":"$q$-Munchausen Reinforcement Learning","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2205.07885","title":"Enforcing KL Regularization in General Tsallis Entropy Reinforcement Learning via Advantage Learning","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2205.15656","title":"Sample-Efficient, Exploration-Based Policy Optimisation for Routing Problems","created":"2022-05-31","cited_by_count":0,"area":null},{"id":"2208.09322","title":"Entropy Augmented Reinforcement Learning","created":"2022-08-19","cited_by_count":0,"area":null},{"id":"2303.01963","title":"Multi-Start Team Orienteering Problem for UAS Mission Re-Planning with Data-Efficient Deep Reinforcement Learning","created":"2023-03-02","cited_by_count":0,"area":null},{"id":"2310.05324","title":"Increasing Entropy to Boost Policy Gradient Performance on Personalization Tasks","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2310.06777","title":"Information Content Exploration","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2312.06527","title":"Can Reinforcement Learning support policy makers? A preliminary study with Integrated Assessment Models","created":"2023-12-11","cited_by_count":0,"area":null},{"id":"2401.00532","title":"On the Necessity of Metalearning: Learning Suitable Parameterizations for Learning Processes","created":"2023-12-31","cited_by_count":0,"area":null},{"id":"2508.18884","title":"HAEPO: History-Aggregated Exploratory Policy Optimization","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2511.05640","title":"Blind Inverse Game Theory: Jointly Decoding Rewards and Rationality in Entropy-Regularized Competitive Games","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2511.18671","title":"Multi-Agent Cross-Entropy Method with Monotonic Nonlinear Critic Decomposition","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2602.03635","title":"TRE: Encouraging Exploration in the Trust Region","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2605.07775","title":"POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2607.23854","title":"Understanding Human-like Solutions in Combinatorial Optimization via Learning and Search","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2610.04011","title":"Exploration-Preserving Policy Optimization","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.15976","title":"Embedding Information in Policy Randomness: Distribution-Preserving Implicit Communication in MDPs","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.20401","title":"Training Language Models to Fail Gracefully","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}