{"list":"other","total":102,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"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":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"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":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","cited_by_count":512},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"2002.05651","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","created":"2020-01-31","cited_by_count":249},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237},{"id":"2410.21845","title":"Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning","created":"2024-10-29","cited_by_count":189},{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184},{"id":"2007.06700","title":"Revisiting Fundamentals of Experience Replay","created":"2020-07-13","cited_by_count":175},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"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":"2205.02824","title":"Rapid Locomotion via Reinforcement Learning","created":"2022-05-05","cited_by_count":168},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"2010.14498","title":"Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning","created":"2020-10-27","cited_by_count":134},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"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":"2203.04181","title":"Selective-Supervised Contrastive Learning with Noisy Labels","created":"2022-03-08","cited_by_count":112},{"id":"2403.10506","title":"HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation","created":"2024-03-15","cited_by_count":112},{"id":"2405.16158","title":"Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control","created":"2024-05-25","cited_by_count":108},{"id":"2402.18762","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","created":"2024-02-29","cited_by_count":86},{"id":"2208.07860","title":"A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning","created":"2022-08-16","cited_by_count":83},{"id":"2402.08609","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","created":"2024-02-13","cited_by_count":78},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78},{"id":"2502.08844","title":"MuJoCo Playground","created":"2025-02-12","cited_by_count":78},{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76},{"id":"2006.05826","title":"Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning","created":"2020-06-10","cited_by_count":75},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65},{"id":"2308.11958","title":"Maintaining Plasticity in Continual Learning via Regenerative Regularization","created":"2023-08-23","cited_by_count":65},{"id":"1704.03073","title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation","created":"2017-04-10","cited_by_count":63},{"id":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61},{"id":"2210.02019","title":"Atari-5: Distilling the Arcade Learning Environment down to Five Games","created":"2022-10-05","cited_by_count":44},{"id":"2505.22642","title":"FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control","created":"2025-05-28","cited_by_count":44},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43},{"id":"2003.06350","title":"Interference and Generalization in Temporal Difference Learning","created":"2020-03-13","cited_by_count":42},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41},{"id":"2402.12479","title":"In value-based deep reinforcement learning, a pruned network is a good network","created":"2024-02-19","cited_by_count":39},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36},{"id":"2304.07939","title":"Leveraging sparse and shared feature activations for disentangled representation learning","created":"2023-04-17","cited_by_count":32},{"id":"2407.01704","title":"Weight Clipping for Deep Continual and Reinforcement Learning","created":"2024-07-01","cited_by_count":29},{"id":"2405.00662","title":"No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO","created":"2024-05-01","cited_by_count":27},{"id":"2405.19153","title":"A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning","created":"2024-05-29","cited_by_count":26},{"id":"1811.06626","title":"The Utility of Sparse Representations for Control in Reinforcement Learning","created":"2018-11-15","cited_by_count":24},{"id":"1909.12255","title":"Harnessing Structures for Value-Based Planning and Reinforcement Learning","created":"2019-09-26","cited_by_count":24},{"id":"2204.00616","title":"Simplicial Embeddings in Self-Supervised Learning and Downstream Classification","created":"2022-04-01","cited_by_count":24},{"id":"2506.15544","title":"Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning","created":"2025-06-18","cited_by_count":23},{"id":"2406.17523","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","created":"2024-06-25","cited_by_count":21},{"id":"2406.18420","title":"Mixture of Experts in a Mixture of RL settings","created":"2024-06-26","cited_by_count":21},{"id":"2410.07994","title":"Neuroplastic Expansion in Deep Reinforcement Learning","created":"2024-10-10","cited_by_count":18},{"id":"2410.08896","title":"MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL","created":"2024-10-11","cited_by_count":16},{"id":"2310.18777","title":"Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings","created":"2023-10-28","cited_by_count":15},{"id":"2410.01930","title":"Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL","created":"2024-10-02","cited_by_count":14},{"id":"2505.24061","title":"Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning","created":"2025-05-29","cited_by_count":14},{"id":"2506.03404","title":"The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks","created":"2025-06-03","cited_by_count":13},{"id":"2506.17204","title":"Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":11},{"id":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","cited_by_count":11},{"id":"2406.02696","title":"iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning","created":"2024-06-04","cited_by_count":9},{"id":"2411.00392","title":"Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization","created":"2024-11-01","cited_by_count":9},{"id":"2503.00653","title":"Discrete Codebook World Models for Continuous Control","created":"2025-03-01","cited_by_count":9},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7},{"id":"2506.13672","title":"The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning","created":"2025-06-16","cited_by_count":6},{"id":"2505.17749","title":"Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning","created":"2025-05-23","cited_by_count":4},{"id":"1912.04002","title":"Learning Sparse Representations Incrementally in Deep Reinforcement Learning","created":"2019-12-09","cited_by_count":3}],"next_cursor":"100"}