{"list":"other","total":70,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1806.10758","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","created":"2018-06-28","cited_by_count":476},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"id":"2001.05371","title":"Making deep neural networks right for the right scientific reasons by interacting with their explanations","created":"2020-01-15","cited_by_count":142},{"id":"2004.14545","title":"Explainable Deep Learning: A Field Guide for the Uninitiated","created":"2020-04-30","cited_by_count":127},{"id":"2111.06420","title":"Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities","created":"2021-11-11","cited_by_count":125},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123},{"id":"2011.12854","title":"Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations","created":"2020-11-25","cited_by_count":94},{"id":"2202.01459","title":"Concept Bottleneck Model with Additional Unsupervised Concepts","created":"2022-02-03","cited_by_count":79},{"id":"2212.07430","title":"Interactive Concept Bottleneck Models","created":"2022-12-14","cited_by_count":79},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73},{"id":"2011.09464","title":"Counterfactual Credit Assignment in Model-Free Reinforcement Learning","created":"2020-11-18","cited_by_count":64},{"id":"2108.13643","title":"Learning to Synthesize Programs as Interpretable and Generalizable Policies","created":"2021-08-31","cited_by_count":59},{"id":"1904.10729","title":"Neural Logic Reinforcement Learning","created":"2019-04-24","cited_by_count":53},{"id":"2207.14526","title":"Leveraging Explanations in Interactive Machine Learning: An Overview","created":"2022-07-29","cited_by_count":53},{"id":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52},{"id":"2306.01439","title":"Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction","created":"2023-06-02","cited_by_count":46},{"id":"2302.04449","title":"Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals","created":"2023-02-09","cited_by_count":45},{"id":"2204.05514","title":"A Comparative Study of Faithfulness Metrics for Model Interpretability Methods","created":"2022-04-12","cited_by_count":39},{"id":"2109.09904","title":"Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems","created":"2021-09-21","cited_by_count":36},{"id":"1912.04226","title":"Unsupervised Curricula for Visual Meta-Reinforcement Learning","created":"2019-12-09","cited_by_count":34},{"id":"2301.09937","title":"Explainable Deep Reinforcement Learning: State of the Art and Challenges","created":"2023-01-24","cited_by_count":33},{"id":"2110.10963","title":"Neuro-Symbolic Reinforcement Learning with First-Order Logic","created":"2021-10-21","cited_by_count":30},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30},{"id":"2308.13453","title":"Learning to Intervene on Concept Bottlenecks","created":"2023-08-25","cited_by_count":29},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24},{"id":"2112.02290","title":"Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations","created":"2021-12-04","cited_by_count":24},{"id":"2102.09407","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","created":"2021-02-18","cited_by_count":23},{"id":"2107.03178","title":"Levels of explainable artificial intelligence for human-aligned conversational explanations","created":"2021-07-07","cited_by_count":21},{"id":"2105.04837","title":"Rationalization through Concepts","created":"2021-05-11","cited_by_count":19},{"id":"2302.12232","title":"Concept Learning for Interpretable Multi-Agent Reinforcement Learning","created":"2023-02-23","cited_by_count":19},{"id":"2012.02898","title":"Learning Interpretable Concept-Based Models with Human Feedback","created":"2020-12-04","cited_by_count":17},{"id":"2210.05189","title":"Neural Networks are Decision Trees","created":"2022-10-11","cited_by_count":17},{"id":"2211.09771","title":"Boosting Object Representation Learning via Motion and Object Continuity","created":"2022-11-16","cited_by_count":17},{"id":"2205.13728","title":"GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis","created":"2022-05-27","cited_by_count":16},{"id":"2104.09469","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","created":"2021-04-19","cited_by_count":14},{"id":"1804.08597","title":"Towards Symbolic Reinforcement Learning with Common Sense","created":"2018-04-23","cited_by_count":12},{"id":"2203.11547","title":"Explainability in reinforcement learning: perspective and position","created":"2022-03-22","cited_by_count":11},{"id":"2103.04067","title":"Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning","created":"2021-03-06","cited_by_count":9},{"id":"1902.00566","title":"Visual Rationalizations in Deep Reinforcement Learning for Atari Games","created":"2019-02-01","cited_by_count":8},{"id":"2009.03603","title":"Evolutionary Reinforcement Learning via Cooperative Coevolutionary Negatively Correlated Search","created":"2020-09-08","cited_by_count":8},{"id":"2210.15906","title":"Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences","created":"2022-10-28","cited_by_count":7},{"id":"2303.12578","title":"Neuro-Symbolic Reasoning Shortcuts: Mitigation Strategies and their Limitations","created":"2023-03-22","cited_by_count":7},{"id":"2211.09937","title":"Explainability Via Causal Self-Talk","created":"2022-11-17","cited_by_count":6},{"id":"1809.09703","title":"A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees","created":"2018-09-25","cited_by_count":5}],"next_cursor":null}