{"total":60,"rows":[{"id":"2402.14528","title":"ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization","created":"2024-02-22","cited_by_count":16,"area":"deeprl"},{"id":"2407.09905","title":"Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods","created":"2024-07-13","cited_by_count":15,"area":"deeprl"},{"id":"2403.02290","title":"Koopman-Assisted Reinforcement Learning","created":"2024-03-04","cited_by_count":11,"area":"deeprl"},{"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":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2503.23631","title":"Intrinsically-Motivated Humans and Agents in Open-World Exploration","created":"2025-03-31","cited_by_count":8,"area":"deeprl"},{"id":"2506.05615","title":"When Maximum Entropy Misleads Policy Optimization","created":"2025-06-05","cited_by_count":7,"area":"deeprl"},{"id":"2406.02295","title":"How to Explore with Belief: State Entropy Maximization in POMDPs","created":"2024-06-04","cited_by_count":6,"area":"deeprl"},{"id":"2407.09247","title":"Constrained Intrinsic Motivation for Reinforcement Learning","created":"2024-07-12","cited_by_count":6,"area":"deeprl"},{"id":"2407.13364","title":"Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2407.13755","title":"Random Latent Exploration for Deep Reinforcement Learning","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2506.07085","title":"State Entropy Regularization for Robust Reinforcement Learning","created":"2025-06-08","cited_by_count":6,"area":"deeprl"},{"id":"2405.19080","title":"OMPO: A Unified Framework for RL under Policy and Dynamics Shifts","created":"2024-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2410.05673","title":"Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem","created":"2024-10-08","cited_by_count":5,"area":"deeprl"},{"id":"2405.17243","title":"Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning","created":"2024-05-27","cited_by_count":4,"area":"deeprl"},{"id":"2405.19807","title":"MetaCURL: Non-stationary Concave Utility Reinforcement Learning","created":"2024-05-30","cited_by_count":4,"area":"deeprl"},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2408.12130","title":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning","created":"2024-08-22","cited_by_count":4,"area":"deeprl"},{"id":"2410.06621","title":"Effective Exploration Based on the Structural Information Principles","created":"2024-10-09","cited_by_count":4,"area":"deeprl"},{"id":"2412.14002","title":"Operator Splitting for Convex Constrained Markov Decision Processes","created":"2024-12-18","cited_by_count":4,"area":"deeprl"},{"id":"2505.01336","title":"Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story","created":"2025-05-02","cited_by_count":4,"area":"deeprl"},{"id":"2402.00162","title":"Behind the Myth of Exploration in Policy Gradients","created":"2024-01-31","cited_by_count":3,"area":"deeprl"},{"id":"2404.02235","title":"Is Exploration All You Need? Effective Exploration Characteristics for Transfer in Reinforcement Learning","created":"2024-04-02","cited_by_count":3,"area":"deeprl"},{"id":"2412.06655","title":"Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures","created":"2024-12-09","cited_by_count":3,"area":"deeprl"},{"id":"2602.06769","title":"Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities","created":"2026-02-06","cited_by_count":3,"area":"deeprl"},{"id":"2412.03800","title":"ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy","created":"2024-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2511.11592","title":"Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL","created":"2025-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2603.08518","title":"Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning","created":"2026-03-09","cited_by_count":2,"area":"deeprl"},{"id":"2407.21546","title":"Black Box Meta-Learning Intrinsic Rewards","created":"2024-07-31","cited_by_count":1,"area":"deeprl"},{"id":"2411.14117","title":"Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problems","created":"2024-11-21","cited_by_count":1,"area":"deeprl"},{"id":"2502.07715","title":"Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning","created":"2025-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2503.06101","title":"ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning","created":"2025-03-08","cited_by_count":1,"area":"deeprl"},{"id":"2506.07054","title":"Policy Gradient with Tree Search: Avoiding Local Optimas through Lookahead","created":"2025-06-08","cited_by_count":1,"area":"deeprl"},{"id":"2507.21543","title":"On Policy Stochasticity in Mutual Information Optimal Control of Linear Systems","created":"2025-07-29","cited_by_count":1,"area":"deeprl"},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2509.01432","title":"The Geometry of Nonlinear Reinforcement Learning","created":"2025-09-01","cited_by_count":1,"area":"deeprl"},{"id":"2511.03187","title":"Periodic Skill Discovery","created":"2025-11-05","cited_by_count":1,"area":"deeprl"},{"id":"2512.10042","title":"SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation","created":"2025-12-10","cited_by_count":1,"area":"deeprl"},{"id":"2602.12181","title":"Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria","created":"2026-02-12","cited_by_count":1,"area":"deeprl"},{"id":"2603.12325","title":"Maximum Entropy Exploration Without the Rollouts","created":"2026-03-12","cited_by_count":1,"area":"deeprl"},{"id":"2607.20152","title":"Active Inference as a Convex Markov Decision Process","created":"2026-07-22","cited_by_count":1,"area":"deeprl"},{"id":"2608.03562","title":"Robust General Utility for Reinforcement Learning","created":"2026-08-04","cited_by_count":1,"area":"deeprl"},{"id":"2402.03771","title":"Reinforcement Learning from Bagged Reward","created":"2024-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2412.07177","title":"Effective Reward Specification in Deep Reinforcement Learning","created":"2024-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2501.18086","title":"DIAL: Distribution-Informed Adaptive Learning of Multi-Task Constraints for Safety-Critical Systems","created":"2025-01-30","cited_by_count":0,"area":"deeprl"},{"id":"2504.06355","title":"An Information-Geometric Approach to Artificial Curiosity","created":"2025-04-08","cited_by_count":0,"area":"deeprl"},{"id":"2505.07303","title":"Online Episodic Convex Reinforcement Learning","created":"2025-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2505.17830","title":"Imagine Beyond! Distributionally Robust Auto-Encoding for State Space Coverage in Online Reinforcement Learning","created":"2025-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2509.20509","title":"Complexity-Regularized Proximal Policy Optimization","created":"2025-09-24","cited_by_count":0,"area":"deeprl"},{"id":"2510.25311","title":"Dense and Diverse Goal Coverage in Multi Goal Reinforcement Learning","created":"2025-10-29","cited_by_count":0,"area":"deeprl"},{"id":"2601.18580","title":"K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents","created":"2026-01-26","cited_by_count":0,"area":"deeprl"},{"id":"2601.19810","title":"Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals","created":"2026-01-27","cited_by_count":0,"area":"deeprl"},{"id":"2603.18965","title":"Maximum-Entropy Exploration with Future State-Action Visitation Measures","created":"2026-03-19","cited_by_count":0,"area":"deeprl"},{"id":"2604.28144","title":"Global Optimality for Constrained Exploration via Penalty Regularization","created":"2026-04-30","cited_by_count":0,"area":"deeprl"},{"id":"2606.21271","title":"Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization","created":"2026-06-19","cited_by_count":0,"area":"deeprl"},{"id":"2607.09971","title":"TopoExplore: Homology as an Exploration Signal","created":"2026-07-10","cited_by_count":0,"area":"deeprl"},{"id":"2608.27507","title":"Marginal Coverage Credit Reduces Redundant Exploration in Parallel State-Entropy Optimization","created":"2026-08-27","cited_by_count":0,"area":"deeprl"},{"id":"2609.04005","title":"The Dually Flat Geometry of Planning as Inference","created":"2026-09-03","cited_by_count":0,"area":"deeprl"},{"id":"2609.08642","title":"SUN: Reaching for Novelty in Reinforcement Learning","created":"2026-09-08","cited_by_count":0,"area":"deeprl"},{"id":"2610.02159","title":"When Do Intrinsic Rewards Lead to Exploration?","created":"2026-10-01","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}