{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1703.03864","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","created":"2017-03-10","cited_by_count":574},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"2408.08435","title":"Automated Design of Agentic Systems","created":"2024-08-15","cited_by_count":407},{"id":"2006.11287","title":"Discovering Symbolic Models from Deep Learning with Inductive Biases","created":"2020-06-19","cited_by_count":344},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190},{"id":"1812.02648","title":"Deep Reinforcement Learning and the Deadly Triad","created":"2018-12-06","cited_by_count":174},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"2206.08896","title":"Evolution through Large Models","created":"2022-06-17","cited_by_count":134},{"id":"2303.07507","title":"Loss of Plasticity in Continual Deep Reinforcement Learning","created":"2023-03-13","cited_by_count":121},{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104},{"id":"1802.09596","title":"Tunability: Importance of Hyperparameters of Machine Learning Algorithms","created":"2018-02-26","cited_by_count":99},{"id":"1810.10180","title":"Understanding and correcting pathologies in the training of learned optimizers","created":"2018-10-24","cited_by_count":97},{"id":"2111.05803","title":"Gradients are Not All You Need","created":"2021-11-10","cited_by_count":86},{"id":"2007.08794","title":"Discovering Reinforcement Learning Algorithms","created":"2020-07-17","cited_by_count":77},{"id":"2006.05826","title":"Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning","created":"2020-06-10","cited_by_count":75},{"id":"2405.15568","title":"OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code","created":"2024-05-24","cited_by_count":74},{"id":"2006.05065","title":"Self-Distillation as Instance-Specific Label Smoothing","created":"2020-06-09","cited_by_count":71},{"id":"2202.02306","title":"Rediscovering orbital mechanics with machine learning","created":"2022-02-04","cited_by_count":71},{"id":"1705.10257","title":"Boltzmann Exploration Done Right","created":"2017-05-29","cited_by_count":69},{"id":"1803.02021","title":"Understanding Short-Horizon Bias in Stochastic Meta-Optimization","created":"2018-03-06","cited_by_count":69},{"id":"1910.04098","title":"Improving Generalization in Meta Reinforcement Learning using Learned Objectives","created":"2019-10-09","cited_by_count":68},{"id":"2009.11243","title":"Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves","created":"2020-09-23","cited_by_count":58},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57},{"id":"2012.14905","title":"Meta Learning Backpropagation And Improving It","created":"2020-12-29","cited_by_count":49},{"id":"1903.08894","title":"Towards Characterizing Divergence in Deep Q-Learning","created":"2019-03-21","cited_by_count":43},{"id":"2406.08414","title":"Discovering Preference Optimization Algorithms with and for Large Language Models","created":"2024-06-12","cited_by_count":42},{"id":"2212.04180","title":"evosax: JAX-based Evolution Strategies","created":"2022-12-08","cited_by_count":41},{"id":"1804.00222","title":"Meta-Learning Update Rules for Unsupervised Representation Learning","created":"2018-03-31","cited_by_count":37},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36},{"id":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31},{"id":"2209.08890","title":"An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey","created":"2022-09-19","cited_by_count":28},{"id":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","cited_by_count":23},{"id":"2405.03547","title":"Position: Leverage Foundational Models for Black-Box Optimization","created":"2024-05-06","cited_by_count":21},{"id":"2206.12984","title":"Improving Policy Optimization with Generalist-Specialist Learning","created":"2022-06-26","cited_by_count":20},{"id":"2203.06578","title":"Symbolic Learning to Optimize: Towards Interpretability and Scalability","created":"2022-03-13","cited_by_count":16},{"id":"2310.02782","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","created":"2023-10-04","cited_by_count":16},{"id":"2302.01470","title":"Learning to Optimize for Reinforcement Learning","created":"2023-02-03","cited_by_count":12},{"id":"2406.15042","title":"Behaviour Distillation","created":"2024-06-21","cited_by_count":5}],"next_cursor":null}