{"list":"other","total":52,"rows":[{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"1505.00853","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","created":"2015-05-05","cited_by_count":519},{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253},{"id":"2201.13259","title":"Trajectory balance: Improved credit assignment in GFlowNets","created":"2022-01-31","cited_by_count":251},{"id":"2203.04115","title":"Biological Sequence Design with GFlowNets","created":"2022-03-02","cited_by_count":174},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158},{"id":"2202.13903","title":"Bayesian Structure Learning with Generative Flow Networks","created":"2022-02-28","cited_by_count":153},{"id":"1911.08453","title":"Planning with Goal-Conditioned Policies","created":"2019-11-19","cited_by_count":149},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134},{"id":"2209.12782","title":"Learning GFlowNets from partial episodes for improved convergence and stability","created":"2022-09-26","cited_by_count":132},{"id":"2011.08909","title":"C-Learning: Learning to Achieve Goals via Recursive Classification","created":"2020-11-17","cited_by_count":103},{"id":"2202.04478","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","created":"2022-02-09","cited_by_count":89},{"id":"2302.01687","title":"Better Training of GFlowNets with Local Credit and Incomplete Trajectories","created":"2023-02-03","cited_by_count":85},{"id":"2010.14484","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","created":"2020-10-27","cited_by_count":79},{"id":"2305.07170","title":"Towards Understanding and Improving GFlowNet Training","created":"2023-05-11","cited_by_count":75},{"id":"2302.05446","title":"Robust Scheduling with GFlowNets","created":"2023-01-17","cited_by_count":69},{"id":"2206.03023","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression","created":"2022-06-07","cited_by_count":66},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64},{"id":"2302.00615","title":"GFlowNets for AI-Driven Scientific Discovery","created":"2023-02-01","cited_by_count":63},{"id":"2210.03308","title":"Generative Augmented Flow Networks","created":"2022-10-07","cited_by_count":50},{"id":"2305.19366","title":"Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network","created":"2023-05-30","cited_by_count":50},{"id":"2110.00188","title":"Offline Reinforcement Learning with Reverse Model-based Imagination","created":"2021-10-01","cited_by_count":47},{"id":"2110.13625","title":"Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning","created":"2021-10-26","cited_by_count":47},{"id":"2402.10309","title":"Discrete Probabilistic Inference as Control in Multi-path Environments","created":"2024-02-15","cited_by_count":44},{"id":"2105.13345","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","created":"2021-05-27","cited_by_count":40},{"id":"2007.01995","title":"Bidirectional Model-based Policy Optimization","created":"2020-07-04","cited_by_count":38},{"id":"2302.09465","title":"Stochastic Generative Flow Networks","created":"2023-02-19","cited_by_count":32},{"id":"2302.05793","title":"Distributional GFlowNets with Quantile Flows","created":"2023-02-11","cited_by_count":28},{"id":"2302.04178","title":"DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets","created":"2023-02-08","cited_by_count":27},{"id":"1804.00379","title":"Recall Traces: Backtracking Models for Efficient Reinforcement Learning","created":"2018-04-02","cited_by_count":23},{"id":"1806.09605","title":"Many-Goals Reinforcement Learning","created":"2018-06-22","cited_by_count":22},{"id":"2208.10483","title":"Prioritizing Samples in Reinforcement Learning with Reducible Loss","created":"2022-08-22","cited_by_count":22},{"id":"2006.00900","title":"PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals","created":"2020-06-01","cited_by_count":21},{"id":"2402.07226","title":"Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL","created":"2024-02-11","cited_by_count":21},{"id":"2210.12704","title":"Batch Multi-Fidelity Active Learning with Budget Constraints","created":"2022-10-23","cited_by_count":20},{"id":"2310.20025","title":"GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models","created":"2023-10-30","cited_by_count":20},{"id":"1803.10227","title":"Forward-Backward Reinforcement Learning","created":"2018-03-27","cited_by_count":19},{"id":"2402.05234","title":"QGFN: Controllable Greediness with Action Values","created":"2024-02-07","cited_by_count":18},{"id":"2306.04620","title":"Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design","created":"2023-06-07","cited_by_count":17},{"id":"2107.00306","title":"MHER: Model-based Hindsight Experience Replay","created":"2021-07-01","cited_by_count":15},{"id":"2309.13508","title":"Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout","created":"2023-09-24","cited_by_count":2},{"id":"2312.05044","title":"Backward Learning for Goal-Conditioned Policies","created":"2023-12-08","cited_by_count":2}],"next_cursor":null}