{"total":227,"rows":[{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061,"area":null},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2205.00824","title":"Exploration in Deep Reinforcement Learning: A Survey","created":"2022-05-02","cited_by_count":166,"area":null},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"area":null},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134,"area":null},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107,"area":null},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2201.11927","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","created":"2022-01-28","cited_by_count":71,"area":null},{"id":"2112.01871","title":"Active Inference in Robotics and Artificial Agents: Survey and Challenges","created":"2021-12-03","cited_by_count":52,"area":null},{"id":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","cited_by_count":52,"area":null},{"id":"2202.09467","title":"Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?","created":"2022-02-18","cited_by_count":45,"area":null},{"id":"2402.10309","title":"Discrete Probabilistic Inference as Control in Multi-path Environments","created":"2024-02-15","cited_by_count":44,"area":null},{"id":"2402.02511","title":"PoCo: Policy Composition from and for Heterogeneous Robot Learning","created":"2024-02-04","cited_by_count":42,"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":"2310.02233","title":"Generalized Schr\\\"odinger Bridge Matching","created":"2023-10-03","cited_by_count":40,"area":null},{"id":"2103.07927","title":"Modelling Behavioural Diversity for Learning in Open-Ended Games","created":"2021-03-14","cited_by_count":39,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35,"area":null},{"id":"2410.07927","title":"Efficient Reinforcement Learning with Large Language Model Priors","created":"2024-10-10","cited_by_count":30,"area":null},{"id":"2503.19618","title":"Beyond Verifiable Rewards: Scaling Reinforcement Learning for Language Models to Unverifiable Data","created":"2025-03-25","cited_by_count":29,"area":null},{"id":"2106.13229","title":"Model-Based Reinforcement Learning via Latent-Space Collocation","created":"2021-06-24","cited_by_count":28,"area":null},{"id":"2210.12496","title":"Bayesian Optimization with Conformal Prediction Sets","created":"2022-10-22","cited_by_count":28,"area":null},{"id":"2101.09207","title":"Differentiable Trust Region Layers for Deep Reinforcement Learning","created":"2021-01-22","cited_by_count":25,"area":null},{"id":"2102.07659","title":"Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems","created":"2021-02-15","cited_by_count":24,"area":null},{"id":"2107.07184","title":"MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning","created":"2021-07-15","cited_by_count":24,"area":null},{"id":"2207.06415","title":"The Free Energy Principle for Perception and Action: A Deep Learning Perspective","created":"2022-07-13","cited_by_count":24,"area":null},{"id":"2306.03552","title":"State Regularized Policy Optimization on Data with Dynamics Shift","created":"2023-06-06","cited_by_count":23,"area":null},{"id":"2102.13176","title":"A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning","created":"2021-02-25","cited_by_count":22,"area":null},{"id":"2110.10083","title":"Contrastive Active Inference","created":"2021-10-19","cited_by_count":21,"area":null},{"id":"2203.12592","title":"Your Policy Regularizer is Secretly an Adversary","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20,"area":null},{"id":"2204.05369","title":"Learning Implicit Priors for Motion Optimization","created":"2022-04-11","cited_by_count":20,"area":null},{"id":"2307.10710","title":"Reparameterized Policy Learning for Multimodal Trajectory Optimization","created":"2023-07-20","cited_by_count":20,"area":null},{"id":"2110.13549","title":"Online Variational Filtering and Parameter Learning","created":"2021-10-26","cited_by_count":19,"area":null},{"id":"2212.13936","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","created":"2022-12-28","cited_by_count":19,"area":null},{"id":"2306.10715","title":"Maximum Entropy Heterogeneous-Agent Reinforcement Learning","created":"2023-06-19","cited_by_count":19,"area":null},{"id":"2109.15316","title":"Scalable Online Planning via Reinforcement Learning Fine-Tuning","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2310.03718","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning","created":"2023-10-05","cited_by_count":18,"area":null},{"id":"2104.10190","title":"Outcome-Driven Reinforcement Learning via Variational Inference","created":"2021-04-20","cited_by_count":17,"area":null},{"id":"2110.12080","title":"C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks","created":"2021-10-22","cited_by_count":17,"area":null},{"id":"2111.02997","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","created":"2021-11-04","cited_by_count":17,"area":null},{"id":"2105.04962","title":"Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning","created":"2021-05-11","cited_by_count":16,"area":null},{"id":"2205.15460","title":"Critic Sequential Monte Carlo","created":"2022-05-30","cited_by_count":16,"area":null},{"id":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2105.04321","title":"Reinforcement learning of rare diffusive dynamics","created":"2021-05-10","cited_by_count":15,"area":null},{"id":"2110.12997","title":"Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning","created":"2021-10-25","cited_by_count":15,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2310.06794","title":"$f$-Policy Gradients: A General Framework for Goal Conditioned RL using $f$-Divergences","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2201.11817","title":"Modeling Human Exploration Through Resource-Rational Reinforcement Learning","created":"2022-01-27","cited_by_count":13,"area":null},{"id":"2210.00999","title":"Latent State Marginalization as a Low-cost Approach for Improving Exploration","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2504.02367","title":"Reinforcement Fine-Tuning for Materials Design","created":"2025-04-03","cited_by_count":13,"area":null},{"id":"2311.18644","title":"Exploring the hierarchical structure of human plans via program generation","created":"2023-11-30","cited_by_count":12,"area":null},{"id":"2502.11541","title":"MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training","created":"2025-02-17","cited_by_count":12,"area":null},{"id":"2503.05453","title":"Soft Policy Optimization: Online Off-Policy RL for Sequence Models","created":"2025-03-07","cited_by_count":12,"area":null},{"id":"2602.09021","title":"$\\chi_{0}$: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2305.17109","title":"Reinforcement Learning with Simple Sequence Priors","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2311.04453","title":"Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2503.19612","title":"RL-finetuning LLMs from on- and off-policy data with a single algorithm","created":"2025-03-25","cited_by_count":11,"area":null},{"id":"2602.07132","title":"Discrete Adjoint Matching","created":"2026-02-06","cited_by_count":11,"area":null},{"id":"2103.06859","title":"Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Control","created":"2021-03-11","cited_by_count":10,"area":null},{"id":"2112.02852","title":"Target Entropy Annealing for Discrete Soft Actor-Critic","created":"2021-12-06","cited_by_count":10,"area":null},{"id":"2207.05631","title":"DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization","created":"2022-07-12","cited_by_count":10,"area":null},{"id":"2210.03512","title":"Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes","created":"2022-10-07","cited_by_count":10,"area":null},{"id":"2306.01460","title":"ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2310.04006","title":"Accelerating optimization over the space of probability measures","created":"2023-10-06","cited_by_count":10,"area":null},{"id":"2107.00140","title":"Applications of the Free Energy Principle to Machine Learning and Neuroscience","created":"2021-06-30","cited_by_count":9,"area":null},{"id":"2112.08438","title":"Programmatic Reward Design by Example","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2406.17863","title":"What type of inference is planning?","created":"2024-06-25","cited_by_count":9,"area":null},{"id":"2105.12991","title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","created":"2021-05-27","cited_by_count":8,"area":null},{"id":"2108.07783","title":"Toward a `Standard Model' of Machine Learning","created":"2021-08-17","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":"2201.02715","title":"Low-Rank Constraints for Fast Inference in Structured Models","created":"2022-01-08","cited_by_count":8,"area":null},{"id":"2210.07890","title":"Hierarchical Policy Blending as Inference for Reactive Robot Control","created":"2022-10-14","cited_by_count":8,"area":null},{"id":"2212.01174","title":"Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning","created":"2022-12-02","cited_by_count":8,"area":null},{"id":"2306.06253","title":"Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2403.06328","title":"Distributional Successor Features Enable Zero-Shot Policy Optimization","created":"2024-03-10","cited_by_count":8,"area":null},{"id":"2409.10023","title":"Reinforcement learning-based statistical search strategy for an axion model from flavor","created":"2024-09-16","cited_by_count":8,"area":null},{"id":"2503.21200","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","created":"2025-03-27","cited_by_count":8,"area":null},{"id":"2512.15605","title":"Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction","created":"2025-12-17","cited_by_count":8,"area":null},{"id":"2105.06228","title":"SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning","created":"2021-05-13","cited_by_count":7,"area":null},{"id":"2110.15688","title":"Variational Bayesian Optimistic Sampling","created":"2021-10-29","cited_by_count":7,"area":null},{"id":"2102.11905","title":"Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Driving","created":"2021-02-23","cited_by_count":6,"area":null},{"id":"2104.01040","title":"Distributional Offline Continuous-Time Reinforcement Learning with Neural Physics-Informed PDEs (SciPhy RL for DOCTR-L)","created":"2021-04-02","cited_by_count":6,"area":null},{"id":"2106.15380","title":"Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes","created":"2021-06-29","cited_by_count":6,"area":null},{"id":"2204.05263","title":"Maximum entropy optimal density control of discrete-time linear systems and Schr\\\"odinger bridges","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2206.09453","title":"Bounding Evidence and Estimating Log-Likelihood in VAE","created":"2022-06-19","cited_by_count":6,"area":null},{"id":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","cited_by_count":6,"area":null},{"id":"2310.09833","title":"Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization","created":"2023-10-15","cited_by_count":6,"area":null},{"id":"2410.09355","title":"On Divergence Measures for Training GFlowNets","created":"2024-10-12","cited_by_count":6,"area":null},{"id":"2505.07261","title":"CHD: Coupled Hierarchical Diffusion for Long-Horizon Tasks","created":"2025-05-12","cited_by_count":6,"area":null},{"id":"2103.07356","title":"Hippocampal formation-inspired probabilistic generative model","created":"2021-03-12","cited_by_count":5,"area":null},{"id":"2106.03931","title":"Entropy Regularized Reinforcement Learning Using Large Deviation Theory","created":"2021-06-07","cited_by_count":5,"area":null},{"id":"2108.06898","title":"Neural-to-Tree Policy Distillation with Policy Improvement Criterion","created":"2021-08-16","cited_by_count":5,"area":null},{"id":"2202.01682","title":"How to build a cognitive map: insights from models of the hippocampal formation","created":"2022-02-03","cited_by_count":5,"area":null},{"id":"2203.10592","title":"Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents","created":"2022-03-20","cited_by_count":5,"area":null}],"next_cursor":"100"}