{"list":"other","total":59,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1506.01186","title":"Cyclical Learning Rates for Training Neural Networks","created":"2015-06-03","cited_by_count":629},{"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":"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":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"1705.08292","title":"The Marginal Value of Adaptive Gradient Methods in Machine Learning","created":"2017-05-23","cited_by_count":250},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"1606.01885","title":"Learning to Optimize","created":"2016-06-06","cited_by_count":195},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"1712.06567","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","created":"2017-12-18","cited_by_count":150},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147},{"id":"1703.05407","title":"Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play","created":"2017-03-15","cited_by_count":141},{"id":"1908.03568","title":"Behaviour Suite for Reinforcement Learning","created":"2019-08-09","cited_by_count":132},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125},{"id":"2303.07507","title":"Loss of Plasticity in Continual Deep Reinforcement Learning","created":"2023-03-13","cited_by_count":121},{"id":"1703.04813","title":"Learned Optimizers that Scale and Generalize","created":"2017-03-14","cited_by_count":110},{"id":"2301.08028","title":"A Tutorial on Meta-Reinforcement Learning","created":"2023-01-19","cited_by_count":108},{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104},{"id":"1810.10180","title":"Understanding and correcting pathologies in the training of learned optimizers","created":"2018-10-24","cited_by_count":97},{"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":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74},{"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":"2112.13835","title":"Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies","created":"2021-12-27","cited_by_count":52},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","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":"2203.11860","title":"Practical tradeoffs between memory, compute, and performance in learned optimizers","created":"2022-03-22","cited_by_count":32},{"id":"2310.07418","title":"Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages","created":"2023-10-11","cited_by_count":28},{"id":"2306.17833","title":"Resetting the Optimizer in Deep RL: An Empirical Study","created":"2023-06-30","cited_by_count":26},{"id":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","cited_by_count":23},{"id":"1810.02525","title":"Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods","created":"2018-10-05","cited_by_count":17},{"id":"2310.02782","title":"Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design","created":"2023-10-04","cited_by_count":16},{"id":"2212.01055","title":"Transformer-Based Learned Optimization","created":"2022-12-02","cited_by_count":13},{"id":"2106.03955","title":"Correcting Momentum in Temporal Difference Learning","created":"2021-06-07","cited_by_count":12},{"id":"2302.01470","title":"Learning to Optimize for Reinforcement Learning","created":"2023-02-03","cited_by_count":12},{"id":"2305.11290","title":"Massively Scalable Inverse Reinforcement Learning in Google Maps","created":"2023-05-18","cited_by_count":11}],"next_cursor":null}