{"list":"other","total":60,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2303.01469","title":"Consistency Models","created":"2023-03-02","cited_by_count":1822},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2310.02279","title":"Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion","created":"2023-10-01","cited_by_count":459},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"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":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2310.02557","title":"Generalization in diffusion models arises from geometry-adaptive harmonic representations","created":"2023-10-04","cited_by_count":185},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170},{"id":"2311.16424","title":"Manifold Preserving Guided Diffusion","created":"2023-11-28","cited_by_count":157},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122},{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112},{"id":"2010.04296","title":"CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning","created":"2020-10-08","cited_by_count":109},{"id":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105},{"id":"2008.06043","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","created":"2020-08-13","cited_by_count":93},{"id":"2310.09336","title":"Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task","created":"2023-10-13","cited_by_count":93},{"id":"2406.09358","title":"Understanding Hallucinations in Diffusion Models through Mode Interpolation","created":"2024-06-13","cited_by_count":91},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"id":"1703.02660","title":"Towards Generalization and Simplicity in Continuous Control","created":"2017-03-08","cited_by_count":68},{"id":"2307.05596","title":"Compositional Generalization from First Principles","created":"2023-07-10","cited_by_count":64},{"id":"2107.08221","title":"Visual Representation Learning Does Not Generalize Strongly Within the Same Domain","created":"2021-07-17","cited_by_count":61},{"id":"1804.03720","title":"Gotta Learn Fast: A New Benchmark for Generalization in RL","created":"2018-04-10","cited_by_count":59},{"id":"1902.01378","title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","created":"2019-02-04","cited_by_count":54},{"id":"2207.02200","title":"Offline RL Policies Should be Trained to be Adaptive","created":"2022-07-05","cited_by_count":52},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40},{"id":"2307.16424","title":"MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning","created":"2023-07-31","cited_by_count":40},{"id":"2212.12611","title":"Your diffusion model secretly knows the dimension of the data manifold","created":"2022-12-23","cited_by_count":36},{"id":"2102.13177","title":"Efficient and Interpretable Robot Manipulation with Graph Neural Networks","created":"2021-02-25","cited_by_count":22},{"id":"2204.13661","title":"Toward Compositional Generalization in Object-Oriented World Modeling","created":"2022-04-28","cited_by_count":22},{"id":"2301.05169","title":"Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning","created":"2023-01-12","cited_by_count":22},{"id":"2010.06740","title":"Measuring Visual Generalization in Continuous Control from Pixels","created":"2020-10-13","cited_by_count":21},{"id":"2302.02984","title":"Robust Subtask Learning for Compositional Generalization","created":"2023-02-06","cited_by_count":4},{"id":"2312.16189","title":"OpenRL: A Unified Reinforcement Learning Framework","created":"2023-12-20","cited_by_count":2},{"id":"2404.04682","title":"Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning","created":"2024-04-06","cited_by_count":2},{"id":"2408.13376","title":"Reduce, Reuse, Recycle: Categories for Compositional Reinforcement Learning","created":"2024-08-23","cited_by_count":2}],"next_cursor":null}