{"total":94,"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":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134,"area":null},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104,"area":null},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2203.09637","title":"Investigating Compounding Prediction Errors in Learned Dynamics Models","created":"2022-03-17","cited_by_count":47,"area":null},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2211.02127","title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","created":"2022-11-03","cited_by_count":36,"area":null},{"id":"2302.09465","title":"Stochastic Generative Flow Networks","created":"2023-02-19","cited_by_count":32,"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":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2108.00128","title":"Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control","created":"2021-07-31","cited_by_count":23,"area":null},{"id":"2112.10504","title":"Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic","created":"2021-12-16","cited_by_count":23,"area":null},{"id":"2201.12569","title":"Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes","created":"2022-01-29","cited_by_count":23,"area":null},{"id":"2408.05804","title":"A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals","created":"2024-08-11","cited_by_count":23,"area":null},{"id":"2109.14311","title":"Learning Dynamics Models for Model Predictive Agents","created":"2021-09-29","cited_by_count":22,"area":null},{"id":"2209.13052","title":"Training Efficient Controllers via Analytic Policy Gradient","created":"2022-09-26","cited_by_count":22,"area":null},{"id":"2309.15421","title":"Deep Learning in Deterministic Computational Mechanics","created":"2023-09-27","cited_by_count":21,"area":null},{"id":"2401.15866","title":"Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution","created":"2024-01-29","cited_by_count":21,"area":null},{"id":"2102.12611","title":"Improved Regret Bound and Experience Replay in Regularized Policy Iteration","created":"2021-02-25","cited_by_count":18,"area":null},{"id":"2108.05828","title":"A general class of surrogate functions for stable and efficient reinforcement learning","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2212.02179","title":"Physics-Informed Model-Based Reinforcement Learning","created":"2022-12-05","cited_by_count":18,"area":null},{"id":"2108.10273","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","created":"2021-08-23","cited_by_count":17,"area":null},{"id":"2211.02222","title":"The Benefits of Model-Based Generalization in Reinforcement Learning","created":"2022-11-04","cited_by_count":17,"area":null},{"id":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2105.00371","title":"Discovering Diverse Athletic Jumping Strategies","created":"2021-05-02","cited_by_count":16,"area":null},{"id":"2106.05012","title":"Bayesian Bellman Operators","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2205.15795","title":"A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud","created":"2022-05-31","cited_by_count":16,"area":null},{"id":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2212.08765","title":"Latent Variable Representation for Reinforcement Learning","created":"2022-12-17","cited_by_count":15,"area":null},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2112.00597","title":"Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation","created":"2021-12-01","cited_by_count":13,"area":null},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2201.12243","title":"Joint Differentiable Optimization and Verification for Certified Reinforcement Learning","created":"2022-01-28","cited_by_count":11,"area":null},{"id":"2305.17250","title":"Self-Supervised Reinforcement Learning that Transfers using Random Features","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2103.16977","title":"Solving Heterogeneous General Equilibrium Economic Models with Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":10,"area":null},{"id":"2501.07468","title":"From Screens to Scenes: A Survey of Embodied AI in Healthcare","created":"2025-01-13","cited_by_count":10,"area":null},{"id":"2103.05147","title":"Model-free Policy Learning with Reward Gradients","created":"2021-03-09","cited_by_count":9,"area":null},{"id":"2205.10868","title":"Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2102.11513","title":"Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model","created":"2021-02-23","cited_by_count":8,"area":null},{"id":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2307.02728","title":"Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill Learning","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2310.19927","title":"Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2102.10456","title":"Decaying Clipping Range in Proximal Policy Optimization","created":"2021-02-20","cited_by_count":6,"area":null},{"id":"2110.10007","title":"Gradient-Based Mixed Planning with Symbolic and Numeric Action Parameters","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2204.09418","title":"Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2302.12617","title":"Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains","created":"2023-02-24","cited_by_count":6,"area":null},{"id":"2303.03955","title":"Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning","created":"2023-03-07","cited_by_count":6,"area":null},{"id":"2306.14133","title":"Provably Convergent Policy Optimization via Metric-aware Trust Region Methods","created":"2023-06-25","cited_by_count":6,"area":null},{"id":"2307.08863","title":"Meta-Value Learning: a General Framework for Learning with Learning Awareness","created":"2023-07-17","cited_by_count":6,"area":null},{"id":"2309.12671","title":"How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2310.01706","title":"On Representation Complexity of Model-based and Model-free Reinforcement Learning","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2101.11331","title":"OffCon$^3$: What is state of the art anyway?","created":"2021-01-27","cited_by_count":5,"area":null},{"id":"2206.07536","title":"Autonomous Platoon Control with Integrated Deep Reinforcement Learning and Dynamic Programming","created":"2022-06-15","cited_by_count":5,"area":null},{"id":"2209.07676","title":"Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning","created":"2022-09-16","cited_by_count":5,"area":null},{"id":"2202.02396","title":"A Temporal-Difference Approach to Policy Gradient Estimation","created":"2022-02-04","cited_by_count":4,"area":null},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2105.05716","title":"Acting upon Imagination: when to trust imagined trajectories in model based reinforcement learning","created":"2021-05-12","cited_by_count":3,"area":null},{"id":"2106.01655","title":"Hierarchical Representation Learning for Markov Decision Processes","created":"2021-06-03","cited_by_count":3,"area":null},{"id":"2203.14660","title":"Revisiting Model-based Value Expansion","created":"2022-03-28","cited_by_count":3,"area":null},{"id":"2208.11535","title":"A model-based approach to meta-Reinforcement Learning: Transformers and tree search","created":"2022-08-24","cited_by_count":3,"area":null},{"id":"2305.15249","title":"Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2410.03915","title":"Distribution Guided Active Feature Acquisition","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2103.12999","title":"Discriminator Augmented Model-Based Reinforcement Learning","created":"2021-03-24","cited_by_count":2,"area":null},{"id":"2103.14407","title":"Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow","created":"2021-03-26","cited_by_count":2,"area":null},{"id":"2104.04174","title":"Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning","created":"2021-04-09","cited_by_count":2,"area":null},{"id":"2105.03733","title":"Generative Actor-Critic: An Off-policy Algorithm Using the Push-forward Model","created":"2021-05-08","cited_by_count":2,"area":null},{"id":"2202.04772","title":"GrASP: Gradient-Based Affordance Selection for Planning","created":"2022-02-08","cited_by_count":2,"area":null},{"id":"2302.01491","title":"DiSProD: Differentiable Symbolic Propagation of Distributions for Planning","created":"2023-02-03","cited_by_count":2,"area":null},{"id":"2306.06637","title":"PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm","created":"2023-06-11","cited_by_count":2,"area":null},{"id":"2307.08033","title":"Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning","created":"2023-07-16","cited_by_count":2,"area":null},{"id":"2412.12024","title":"Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2104.10403","title":"Model-aided Deep Reinforcement Learning for Sample-efficient UAV Trajectory Design in IoT Networks","created":"2021-04-21","cited_by_count":1,"area":null},{"id":"2105.02135","title":"UVIP: Model-Free Approach to Evaluate Reinforcement Learning Algorithms","created":"2021-05-05","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":"2107.02711","title":"A Unified Off-Policy Evaluation Approach for General Value Function","created":"2021-07-06","cited_by_count":1,"area":null},{"id":"2110.12306","title":"Fully Distributed Actor-Critic Architecture for Multitask Deep Reinforcement Learning","created":"2021-10-23","cited_by_count":1,"area":null},{"id":"2111.08108","title":"Physics-informed neural networks via stochastic Hamiltonian dynamics learning","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2201.08894","title":"Reinforcement Learning for Personalized Drug Discovery and Design for Complex Diseases: A Systems Pharmacology Perspective","created":"2022-01-21","cited_by_count":1,"area":null},{"id":"2203.09565","title":"Strategic Maneuver and Disruption with Reinforcement Learning Approaches for Multi-Agent Coordination","created":"2022-03-17","cited_by_count":1,"area":null},{"id":"2206.06796","title":"Open-Ended Learning Strategies for Learning Complex Locomotion Skills","created":"2022-06-14","cited_by_count":1,"area":null},{"id":"2306.08810","title":"Deep Generative Models for Decision-Making and Control","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2306.17366","title":"$\\lambda$-models: Effective Decision-Aware Reinforcement Learning with Latent Models","created":"2023-06-30","cited_by_count":1,"area":null},{"id":"2407.12964","title":"Learning Long-Horizon Predictions for Quadrotor Dynamics","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2210.10613","title":"Integrated Decision and Control for High-Level Automated Vehicles by Mixed Policy Gradient and Its Experiment Verification","created":"2022-10-19","cited_by_count":0,"area":null},{"id":"2302.14182","title":"Taylor TD-learning","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2304.03081","title":"Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2307.08168","title":"Enabling Efficient, Reliable Real-World Reinforcement Learning with Approximate Physics-Based Models","created":"2023-07-16","cited_by_count":0,"area":null},{"id":"2309.16291","title":"Efficiency Separation between RL Methods: Model-Free, Model-Based and Goal-Conditioned","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2608.04832","title":"Robust Control under Stationary Ambiguity","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.12890","title":"Large Distant Gradients Need Not Be Reliable: reliability-weighted credit assignment for long-horizon autoregressive forecasting","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.31363","title":"Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}