{"list":"other","total":63,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"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":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1609.05807","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","created":"2016-09-19","cited_by_count":586},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"1702.03037","title":"Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2017-02-10","cited_by_count":209},{"id":"1908.09453","title":"OpenSpiel: A Framework for Reinforcement Learning in Games","created":"2019-08-26","cited_by_count":186},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170},{"id":"1703.06748","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","created":"2017-03-08","cited_by_count":166},{"id":"2003.04664","title":"Automatic Curriculum Learning For Deep RL: A Short Survey","created":"2020-03-10","cited_by_count":150},{"id":"1906.08386","title":"Inherent Tradeoffs in Learning Fair Representations","created":"2019-06-19","cited_by_count":144},{"id":"1810.08810","title":"The Frontiers of Fairness in Machine Learning","created":"2018-10-20","cited_by_count":141},{"id":"2206.15378","title":"Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning","created":"2022-06-30","cited_by_count":131},{"id":"2010.01523","title":"RODE: Learning Roles to Decompose Multi-Agent Tasks","created":"2020-10-04","cited_by_count":125},{"id":"1803.08884","title":"Inequity aversion improves cooperation in intertemporal social dilemmas","created":"2018-03-23","cited_by_count":106},{"id":"1705.06452","title":"Delving into adversarial attacks on deep policies","created":"2017-05-18","cited_by_count":104},{"id":"2004.13332","title":"The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies","created":"2020-04-28","cited_by_count":75},{"id":"2008.01825","title":"Robust Reinforcement Learning using Adversarial Populations","created":"2020-08-04","cited_by_count":66},{"id":"1907.01439","title":"Operationalizing Individual Fairness with Pairwise Fair Representations","created":"2019-07-02","cited_by_count":64},{"id":"1709.02865","title":"Prosocial learning agents solve generalized Stag Hunts better than selfish ones","created":"2017-09-08","cited_by_count":47},{"id":"1706.09773","title":"Interpretability via Model Extraction","created":"2017-06-29","cited_by_count":40},{"id":"2012.09421","title":"Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning","created":"2020-12-17","cited_by_count":40},{"id":"2106.00285","title":"Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning","created":"2021-06-01","cited_by_count":38},{"id":"2210.00849","title":"Scaling Laws for a Multi-Agent Reinforcement Learning Model","created":"2022-09-29","cited_by_count":38},{"id":"2105.15164","title":"DISSECT: Disentangled Simultaneous Explanations via Concept Traversals","created":"2021-05-31","cited_by_count":37},{"id":"1809.05188","title":"CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning","created":"2018-09-13","cited_by_count":31},{"id":"1811.05931","title":"Evolving intrinsic motivations for altruistic behavior","created":"2018-11-14","cited_by_count":30},{"id":"2211.00241","title":"Adversarial Policies Beat Superhuman Go AIs","created":"2022-11-01","cited_by_count":29},{"id":"2101.05507","title":"Evaluating the Robustness of Collaborative Agents","created":"2021-01-14","cited_by_count":25},{"id":"2205.06760","title":"Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning","created":"2022-05-13","cited_by_count":19},{"id":"2102.05975","title":"Investigating Trade-offs in Utility, Fairness and Differential Privacy in Neural Networks","created":"2021-02-11","cited_by_count":17},{"id":"2211.03769","title":"Are AlphaZero-like Agents Robust to Adversarial Perturbations?","created":"2022-11-07","cited_by_count":14},{"id":"2006.12478","title":"Ecological Reinforcement Learning","created":"2020-06-22","cited_by_count":13},{"id":"2011.14890","title":"Low-Bandwidth Communication Emerges Naturally in Multi-Agent Learning Systems","created":"2020-11-30","cited_by_count":7},{"id":"1812.11276","title":"Learn to Interpret Atari Agents","created":"2018-12-29","cited_by_count":6},{"id":"2206.09046","title":"Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis","created":"2022-06-17","cited_by_count":3}],"next_cursor":null}