{"total":332,"rows":[{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392,"area":null},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290,"area":null},{"id":"2101.03288","title":"How to Train Your Energy-Based Models","created":"2021-01-09","cited_by_count":274,"area":null},{"id":"2201.13259","title":"Trajectory balance: Improved credit assignment in GFlowNets","created":"2022-01-31","cited_by_count":251,"area":null},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"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":"2203.04115","title":"Biological Sequence Design with GFlowNets","created":"2022-03-02","cited_by_count":174,"area":null},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134,"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":"2202.01361","title":"Generative Flow Networks for Discrete Probabilistic Modeling","created":"2022-02-03","cited_by_count":114,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104,"area":null},{"id":"2210.12765","title":"Multi-Objective GFlowNets","created":"2022-10-23","cited_by_count":101,"area":null},{"id":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97,"area":null},{"id":"2302.01687","title":"Better Training of GFlowNets with Local Credit and Incomplete Trajectories","created":"2023-02-03","cited_by_count":85,"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":"2102.01585","title":"Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning","created":"2021-02-02","cited_by_count":73,"area":null},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","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":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70,"area":null},{"id":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67,"area":null},{"id":"2306.16156","title":"Recent Advances in Optimal Transport for Machine Learning","created":"2023-06-28","cited_by_count":66,"area":null},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64,"area":null},{"id":"2304.07297","title":"Language Instructed Reinforcement Learning for Human-AI Coordination","created":"2023-04-13","cited_by_count":63,"area":null},{"id":"2104.03086","title":"Trajectory Prediction with Latent Belief Energy-Based Model","created":"2021-04-07","cited_by_count":60,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2211.03464","title":"A Survey on Quantum Reinforcement Learning","created":"2022-11-07","cited_by_count":53,"area":null},{"id":"2210.03308","title":"Generative Augmented Flow Networks","created":"2022-10-07","cited_by_count":50,"area":null},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"area":null},{"id":"2110.06267","title":"Twice regularized MDPs and the equivalence between robustness and regularization","created":"2021-10-12","cited_by_count":47,"area":null},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"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":"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":"2305.17010","title":"Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets","created":"2023-05-26","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":"2109.07719","title":"Efficient Differentiable Simulation of Articulated Bodies","created":"2021-09-16","cited_by_count":39,"area":null},{"id":"2205.01758","title":"Differentiable Simulation of Soft Multi-body Systems","created":"2022-05-03","cited_by_count":39,"area":null},{"id":"2402.05961","title":"Genetic-guided GFlowNets for Sample Efficient Molecular Optimization","created":"2024-02-05","cited_by_count":39,"area":null},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2112.09559","title":"ColO-RAN: Developing Machine Learning-based xApps for Open RAN Closed-loop Control on Programmable Experimental Platforms","created":"2021-12-17","cited_by_count":35,"area":null},{"id":"2110.08923","title":"A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization","created":"2021-10-17","cited_by_count":34,"area":null},{"id":"2507.07986","title":"EXPO: Stable Reinforcement Learning with Expressive Policies","created":"2025-07-10","cited_by_count":34,"area":null},{"id":"2303.08059","title":"Fast Rates for Maximum Entropy Exploration","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2302.09465","title":"Stochastic Generative Flow Networks","created":"2023-02-19","cited_by_count":32,"area":null},{"id":"2306.17693","title":"Thompson sampling for improved exploration in GFlowNets","created":"2023-06-30","cited_by_count":32,"area":null},{"id":"2305.18901","title":"Policy Optimization for Continuous Reinforcement Learning","created":"2023-05-30","cited_by_count":31,"area":null},{"id":"2312.14331","title":"Maximum entropy GFlowNets with soft Q-learning","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2106.10517","title":"A Max-Min Entropy Framework for Reinforcement Learning","created":"2021-06-19","cited_by_count":28,"area":null},{"id":"2310.02823","title":"Learning to Scale Logits for Temperature-Conditional GFlowNets","created":"2023-10-04","cited_by_count":27,"area":null},{"id":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2405.01155","title":"SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints","created":"2024-05-02","cited_by_count":26,"area":null},{"id":"2105.11674","title":"Unbiased Asymmetric Reinforcement Learning under Partial Observability","created":"2021-05-25","cited_by_count":25,"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":"2310.05858","title":"Distributional Soft Actor-Critic with Three Refinements","created":"2023-10-09","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":"2106.04335","title":"Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization","created":"2021-06-08","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":"2306.03552","title":"State Regularized Policy Optimization on Data with Dynamics Shift","created":"2023-06-06","cited_by_count":23,"area":null},{"id":"2310.02951","title":"A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces","created":"2023-10-04","cited_by_count":23,"area":null},{"id":"2102.08370","title":"Quantifying the effects of environment and population diversity in multi-agent reinforcement learning","created":"2021-02-16","cited_by_count":22,"area":null},{"id":"2105.12540","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation","created":"2021-05-26","cited_by_count":22,"area":null},{"id":"2202.02886","title":"Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity","created":"2022-02-06","cited_by_count":22,"area":null},{"id":"2205.14590","title":"Independent and Decentralized Learning in Markov Potential Games","created":"2022-05-29","cited_by_count":22,"area":null},{"id":"2211.09721","title":"A Finite-Particle Convergence Rate for Stein Variational Gradient Descent","created":"2022-11-17","cited_by_count":22,"area":null},{"id":"2102.11866","title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality","created":"2021-02-23","cited_by_count":21,"area":null},{"id":"2110.12628","title":"Recurrent Off-policy Baselines for Memory-based Continuous Control","created":"2021-10-25","cited_by_count":21,"area":null},{"id":"2201.07296","title":"Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime","created":"2022-01-18","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":"2305.12393","title":"Layer Collaboration in the Forward-Forward Algorithm","created":"2023-05-21","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":"2205.14327","title":"Efficient Policy Iteration for Robust Markov Decision Processes via Regularization","created":"2022-05-28","cited_by_count":20,"area":null},{"id":"2103.00107","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","created":"2021-02-27","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":"2410.14250","title":"Vision-Language Navigation with Energy-Based Policy","created":"2024-10-18","cited_by_count":19,"area":null},{"id":"2106.12506","title":"Sampling with Mirrored Stein Operators","created":"2021-06-23","cited_by_count":17,"area":null},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","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":"2310.00239","title":"AdaptNet: Policy Adaptation for Physics-Based Character Control","created":"2023-09-30","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":"2110.00304","title":"Divergence-Regularized Multi-Agent Actor-Critic","created":"2021-10-01","cited_by_count":15,"area":null},{"id":"2112.11921","title":"Variational Quantum Soft Actor-Critic","created":"2021-12-20","cited_by_count":15,"area":null},{"id":"2212.09010","title":"Risk-Sensitive Reinforcement Learning with Exponential Criteria","created":"2022-12-18","cited_by_count":15,"area":null},{"id":"2301.05579","title":"A survey and taxonomy of loss functions in machine learning","created":"2023-01-13","cited_by_count":15,"area":null},{"id":"2303.01049","title":"Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing","created":"2023-03-02","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":"2409.08469","title":"Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent","created":"2024-09-13","cited_by_count":14,"area":null},{"id":"2410.15474","title":"Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization","created":"2024-10-20","cited_by_count":14,"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":"2302.12537","title":"Why Target Networks Stabilise Temporal Difference Methods","created":"2023-02-24","cited_by_count":13,"area":null},{"id":"2305.14076","title":"Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent","created":"2023-05-23","cited_by_count":13,"area":null},{"id":"2310.00386","title":"Order-Preserving GFlowNets","created":"2023-09-30","cited_by_count":13,"area":null},{"id":"2511.15248","title":"EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control","created":"2025-11-19","cited_by_count":13,"area":null},{"id":"2404.07732","title":"Monte Carlo Tree Search with Boltzmann Exploration","created":"2024-04-11","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":"2210.08708","title":"Teacher Forcing Recovers Reward Functions for Text Generation","created":"2022-10-17","cited_by_count":11,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","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}],"next_cursor":"100"}