{"list":"other","total":107,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264},{"id":"1611.01796","title":"Modular Multitask Reinforcement Learning with Policy Sketches","created":"2016-11-06","cited_by_count":203},{"id":"2402.04825","title":"Fast Timing-Conditioned Latent Audio Diffusion","created":"2024-02-07","cited_by_count":181},{"id":"1906.02569","title":"Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild","created":"2019-06-06","cited_by_count":178},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170},{"id":"2009.06489","title":"The Hardware Lottery","created":"2020-09-14","cited_by_count":160},{"id":"2310.08710","title":"Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research","created":"2023-10-12","cited_by_count":160},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139},{"id":"2401.16013","title":"SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning","created":"2024-01-29","cited_by_count":136},{"id":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122},{"id":"1810.00123","title":"Generalization and Regularization in DQN","created":"2018-09-29","cited_by_count":118},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109},{"id":"2101.02722","title":"The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels","created":"2021-01-07","cited_by_count":100},{"id":"1706.05064","title":"Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning","created":"2017-06-15","cited_by_count":98},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97},{"id":"2306.00937","title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","created":"2023-06-01","cited_by_count":97},{"id":"1604.07255","title":"A Deep Hierarchical Approach to Lifelong Learning in Minecraft","created":"2016-04-25","cited_by_count":90},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"id":"1704.08795","title":"Mapping Instructions and Visual Observations to Actions with Reinforcement Learning","created":"2017-04-28","cited_by_count":81},{"id":"1806.10729","title":"Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation","created":"2018-06-28","cited_by_count":81},{"id":"2011.14826","title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","created":"2020-11-20","cited_by_count":78},{"id":"1712.07294","title":"Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning","created":"2017-12-20","cited_by_count":77},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70},{"id":"2008.09293","title":"A Composable Specification Language for Reinforcement Learning Tasks","created":"2020-08-21","cited_by_count":69},{"id":"2207.03530","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","created":"2022-07-07","cited_by_count":68},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63},{"id":"1804.03720","title":"Gotta Learn Fast: A New Benchmark for Generalization in RL","created":"2018-04-10","cited_by_count":59},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59},{"id":"2306.09884","title":"Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX","created":"2023-06-16","cited_by_count":58},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55},{"id":"2303.17503","title":"Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning","created":"2023-03-29","cited_by_count":51},{"id":"1806.07377","title":"Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation","created":"2018-05-31","cited_by_count":50},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46},{"id":"2002.06432","title":"PDDLGym: Gym Environments from PDDL Problems","created":"2020-02-15","cited_by_count":45},{"id":"1509.00413","title":"Program Synthesis using Natural Language","created":"2015-09-01","cited_by_count":41},{"id":"2109.08267","title":"CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research","created":"2021-09-17","cited_by_count":41},{"id":"2101.04808","title":"MLGO: a Machine Learning Guided Compiler Optimizations Framework","created":"2021-01-13","cited_by_count":40},{"id":"1401.5390","title":"Learning to Win by Reading Manuals in a Monte-Carlo Framework","created":"2014-01-18","cited_by_count":39},{"id":"1905.05013","title":"Ludii -- The Ludemic General Game System","created":"2019-05-13","cited_by_count":39},{"id":"2312.03801","title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","created":"2023-12-06","cited_by_count":39},{"id":"1910.08210","title":"RTFM: Generalising to Novel Environment Dynamics via Reading","created":"2019-10-18","cited_by_count":33},{"id":"2407.03321","title":"Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages","created":"2024-07-03","cited_by_count":33},{"id":"2011.06363","title":"Griddly: A platform for AI research in games","created":"2020-11-12","cited_by_count":31},{"id":"2303.03376","title":"MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning","created":"2023-03-06","cited_by_count":31},{"id":"2007.15543","title":"PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards","created":"2020-07-30","cited_by_count":30},{"id":"2303.12642","title":"Democratising AI: Multiple Meanings, Goals, and Methods","created":"2023-03-22","cited_by_count":29},{"id":"2105.08541","title":"DACBench: A Benchmark Library for Dynamic Algorithm Configuration","created":"2021-05-18","cited_by_count":28},{"id":"2403.17381","title":"Application-Driven Innovation in Machine Learning","created":"2024-03-26","cited_by_count":24},{"id":"2407.09388","title":"GAVEL: Generating Games Via Evolution and Language Models","created":"2024-07-12","cited_by_count":24},{"id":"1903.00714","title":"A Cooperative Multi-Agent Reinforcement Learning Framework for Resource Balancing in Complex Logistics Network","created":"2019-03-02","cited_by_count":22},{"id":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","cited_by_count":20},{"id":"1710.03850","title":"Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer","created":"2017-10-10","cited_by_count":19},{"id":"2009.00541","title":"\"It's Unwieldy and It Takes a Lot of Time.\" Challenges and Opportunities for Creating Agents in Commercial Games","created":"2020-09-01","cited_by_count":17},{"id":"2308.00109","title":"A Sentence is Worth a Thousand Pictures: Can Large Language Models Understand Hum4n L4ngu4ge and the W0rld behind W0rds?","created":"2023-07-26","cited_by_count":17},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","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":"2308.13289","title":"JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading","created":"2023-08-25","cited_by_count":14},{"id":"2405.13242","title":"Goals as Reward-Producing Programs","created":"2024-05-21","cited_by_count":14},{"id":"2406.03348","title":"Position: A Call to Action for a Human-Centered AutoML Paradigm","created":"2024-06-05","cited_by_count":14},{"id":"2306.09205","title":"Reward-Free Curricula for Training Robust World Models","created":"2023-06-15","cited_by_count":13},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9},{"id":"2107.01078","title":"General Board Game Concepts","created":"2021-07-02","cited_by_count":8},{"id":"2304.02396","title":"AutoRL Hyperparameter Landscapes","created":"2023-04-05","cited_by_count":8},{"id":"2101.09562","title":"Deep Learning for General Game Playing with Ludii and Polygames","created":"2021-01-23","cited_by_count":7},{"id":"2105.14780","title":"Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning","created":"2021-05-31","cited_by_count":7},{"id":"1809.00397","title":"Visual Transfer between Atari Games using Competitive Reinforcement Learning","created":"2018-09-02","cited_by_count":5},{"id":"2006.08295","title":"Efficient Reasoning in Regular Boardgames","created":"2020-06-15","cited_by_count":5},{"id":"2301.03913","title":"Measuring Board Game Distance","created":"2023-01-10","cited_by_count":5},{"id":"2208.06448","title":"RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents","created":"2022-08-12","cited_by_count":4},{"id":"2301.01320","title":"Towards Deployable RL -- What's Broken with RL Research and a Potential Fix","created":"2023-01-03","cited_by_count":4},{"id":"1906.00336","title":"The Principle of Unchanged Optimality in Reinforcement Learning Generalization","created":"2019-06-02","cited_by_count":3},{"id":"2009.05643","title":"The Design Of \"Stratega\": A General Strategy Games Framework","created":"2020-09-11","cited_by_count":3}],"next_cursor":"100"}