{"list":"other","total":56,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"2301.07067","title":"Transformers as Algorithms: Generalization and Stability in In-context Learning","created":"2023-01-17","cited_by_count":222},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2003.02979","title":"\"Other-Play\" for Zero-Shot Coordination","created":"2020-03-06","cited_by_count":198},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190},{"id":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164},{"id":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139},{"id":"1910.13616","title":"Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation","created":"2019-10-30","cited_by_count":103},{"id":"1810.06784","title":"ProMP: Proximal Meta-Policy Search","created":"2018-10-16","cited_by_count":91},{"id":"1703.02949","title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","created":"2017-03-08","cited_by_count":85},{"id":"2103.04000","title":"Off-Belief Learning","created":"2021-03-06","cited_by_count":75},{"id":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70},{"id":"2006.09447","title":"Agent Modelling under Partial Observability for Deep Reinforcement Learning","created":"2020-06-16","cited_by_count":57},{"id":"2003.10423","title":"Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning","created":"2020-03-23","cited_by_count":48},{"id":"2302.13335","title":"Diffusion Model-Augmented Behavioral Cloning","created":"2023-02-26","cited_by_count":38},{"id":"2204.11828","title":"Skill-based Meta-Reinforcement Learning","created":"2022-04-25","cited_by_count":37},{"id":"2302.01605","title":"Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased","created":"2023-02-03","cited_by_count":37},{"id":"2102.05714","title":"Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation","created":"2021-02-10","cited_by_count":35},{"id":"2106.06613","title":"A New Formalism, Method and Open Issues for Zero-Shot Coordination","created":"2021-06-11","cited_by_count":33},{"id":"2302.04831","title":"Cooperative Open-ended Learning Framework for Zero-shot Coordination","created":"2023-02-09","cited_by_count":30},{"id":"2305.16683","title":"Future-conditioned Unsupervised Pretraining for Decision Transformer","created":"2023-05-26","cited_by_count":26},{"id":"2301.06387","title":"PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination","created":"2023-01-16","cited_by_count":25},{"id":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24},{"id":"2310.05208","title":"ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination","created":"2023-10-08","cited_by_count":24},{"id":"2411.13934","title":"Learning to Cooperate with Humans using Generative Agents","created":"2024-11-21","cited_by_count":24},{"id":"2201.12436","title":"Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination","created":"2022-01-28","cited_by_count":23},{"id":"2011.05373","title":"Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences","created":"2020-11-10","cited_by_count":21},{"id":"2405.16194","title":"Diffusion-Reward Adversarial Imitation Learning","created":"2024-05-25","cited_by_count":20},{"id":"2403.06826","title":"In-context Exploration-Exploitation for Reinforcement Learning","created":"2024-03-11","cited_by_count":16},{"id":"2504.12714","title":"Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination","created":"2025-04-17","cited_by_count":14},{"id":"2410.05429","title":"Diffusion Imitation from Observation","created":"2024-10-07","cited_by_count":13},{"id":"2208.04957","title":"Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution","created":"2022-08-09","cited_by_count":12},{"id":"2308.10284","title":"Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi","created":"2023-08-20","cited_by_count":10},{"id":"2402.02468","title":"Fast Peer Adaptation with Context-aware Exploration","created":"2024-02-04","cited_by_count":7},{"id":"2306.09309","title":"Who Needs to Know? Minimal Knowledge for Optimal Coordination","created":"2023-06-15","cited_by_count":5},{"id":"2505.17323","title":"Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)","created":"2025-05-22","cited_by_count":4}],"next_cursor":null}