{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"2201.13259","title":"Trajectory balance: Improved credit assignment in GFlowNets","created":"2022-01-31","cited_by_count":251},{"id":"1903.02741","title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","created":"2019-03-07","cited_by_count":226},{"id":"1906.06195","title":"R2D2: Repeatable and Reliable Detector and Descriptor","created":"2019-06-14","cited_by_count":207},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197},{"id":"2203.04115","title":"Biological Sequence Design with GFlowNets","created":"2022-03-02","cited_by_count":174},{"id":"1807.04225","title":"Measuring abstract reasoning in neural networks","created":"2018-07-11","cited_by_count":166},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138},{"id":"2209.12782","title":"Learning GFlowNets from partial episodes for improved convergence and stability","created":"2022-09-26","cited_by_count":132},{"id":"2301.08028","title":"A Tutorial on Meta-Reinforcement Learning","created":"2023-01-19","cited_by_count":108},{"id":"2210.12765","title":"Multi-Objective GFlowNets","created":"2022-10-23","cited_by_count":101},{"id":"2305.07141","title":"The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain","created":"2023-05-11","cited_by_count":101},{"id":"1609.05521","title":"Playing FPS Games with Deep Reinforcement Learning","created":"2016-09-18","cited_by_count":95},{"id":"2305.18354","title":"LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations","created":"2023-05-26","cited_by_count":82},{"id":"2302.05446","title":"Robust Scheduling with GFlowNets","created":"2023-01-17","cited_by_count":69},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66},{"id":"2311.09247","title":"Comparing Humans, GPT-4, and GPT-4V On Abstraction and Reasoning Tasks","created":"2023-11-14","cited_by_count":55},{"id":"1902.00120","title":"Learning to Make Analogies by Contrasting Abstract Relational Structure","created":"2019-01-31","cited_by_count":53},{"id":"2305.17010","title":"Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets","created":"2023-05-26","cited_by_count":40},{"id":"2007.05059","title":"Learning Representations that Support Extrapolation","created":"2020-07-09","cited_by_count":36},{"id":"2106.07824","title":"Communicating Natural Programs to Humans and Machines","created":"2021-06-15","cited_by_count":35},{"id":"2103.05823","title":"Fast and flexible: Human program induction in abstract reasoning tasks","created":"2021-03-10","cited_by_count":33},{"id":"2202.10284","title":"A Review of Emerging Research Directions in Abstract Visual Reasoning","created":"2022-02-21","cited_by_count":33},{"id":"2210.09880","title":"Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus","created":"2022-10-18","cited_by_count":32},{"id":"2403.11793","title":"Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus","created":"2024-03-18","cited_by_count":32},{"id":"2110.11536","title":"Neural-guided, Bidirectional Program Search for Abstraction and Reasoning","created":"2021-10-22","cited_by_count":23},{"id":"2402.04858","title":"CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay","created":"2024-02-07","cited_by_count":23},{"id":"2004.12193","title":"Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning","created":"2020-04-25","cited_by_count":18},{"id":"2303.04091","title":"Abstract Visual Reasoning Enabled by Language","created":"2023-03-07","cited_by_count":15},{"id":"2306.08204","title":"Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer","created":"2023-06-14","cited_by_count":12},{"id":"2302.09425","title":"A Neurodiversity-Inspired Solver for the Abstraction \\& Reasoning Corpus (ARC) Using Visual Imagery and Program Synthesis","created":"2023-02-18","cited_by_count":9},{"id":"2311.08083","title":"Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized method","created":"2023-11-14","cited_by_count":8},{"id":"2301.03094","title":"A Divide-Align-Conquer Strategy for Program Synthesis","created":"2023-01-08","cited_by_count":7},{"id":"2104.03589","title":"PQA: Perceptual Question Answering","created":"2021-04-08","cited_by_count":6},{"id":"2211.16315","title":"Learning and Understanding a Disentangled Feature Representation for Hidden Parameters in Reinforcement Learning","created":"2022-11-29","cited_by_count":1}],"next_cursor":null}