{"list":"other","total":59,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"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":"1603.00943","title":"CVXPY: A Python-Embedded Modeling Language for Convex Optimization","created":"2016-03-03","cited_by_count":641},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"1910.07969","title":"On Completeness-aware Concept-Based Explanations in Deep Neural Networks","created":"2019-10-17","cited_by_count":239},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"id":"1907.07165","title":"Explaining Classifiers with Causal Concept Effect (CaCE)","created":"2019-07-16","cited_by_count":135},{"id":"2106.13314","title":"Promises and Pitfalls of Black-Box Concept Learning Models","created":"2021-06-24","cited_by_count":131},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123},{"id":"2212.11870","title":"Impossibility Theorems for Feature Attribution","created":"2022-12-22","cited_by_count":78},{"id":"2306.09200","title":"ChessGPT: Bridging Policy Learning and Language Modeling","created":"2023-06-15","cited_by_count":75},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73},{"id":"1602.02658","title":"Graying the black box: Understanding DQNs","created":"2016-02-08","cited_by_count":68},{"id":"1805.07039","title":"A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations","created":"2018-05-18","cited_by_count":60},{"id":"1912.05743","title":"Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning","created":"2019-12-09","cited_by_count":60},{"id":"2209.11222","title":"Concept Activation Regions: A Generalized Framework For Concept-Based Explanations","created":"2022-09-22","cited_by_count":57},{"id":"1912.12191","title":"Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution","created":"2019-12-23","cited_by_count":50},{"id":"1609.05518","title":"Towards Deep Symbolic Reinforcement Learning","created":"2016-09-18","cited_by_count":42},{"id":"1811.12530","title":"Learning Finite State Representations of Recurrent Policy Networks","created":"2018-11-29","cited_by_count":37},{"id":"2105.15164","title":"DISSECT: Disentangled Simultaneous Explanations via Concept Traversals","created":"2021-05-31","cited_by_count":37},{"id":"1907.05855","title":"DisCoRL: Continual Reinforcement Learning via Policy Distillation","created":"2019-07-11","cited_by_count":36},{"id":"2002.01080","title":"Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations","created":"2020-02-04","cited_by_count":32},{"id":"2007.11500","title":"Debiasing Concept-based Explanations with Causal Analysis","created":"2020-07-22","cited_by_count":32},{"id":"2202.08434","title":"A Survey of Explainable Reinforcement Learning","created":"2022-02-17","cited_by_count":31},{"id":"1911.11293","title":"Efficient Saliency Maps for Explainable AI","created":"2019-11-26","cited_by_count":30},{"id":"1907.01180","title":"Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy","created":"2019-07-02","cited_by_count":29},{"id":"2209.14279","title":"Causal Proxy Models for Concept-Based Model Explanations","created":"2022-09-28","cited_by_count":29},{"id":"1901.08651","title":"Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics","created":"2019-01-24","cited_by_count":21},{"id":"2208.14966","title":"Concept Gradient: Concept-based Interpretation Without Linear Assumption","created":"2022-08-31","cited_by_count":20},{"id":"2309.12482","title":"State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding","created":"2023-09-21","cited_by_count":17},{"id":"1904.01318","title":"Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents","created":"2019-04-02","cited_by_count":15},{"id":"2009.04374","title":"Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess","created":"2020-09-09","cited_by_count":15},{"id":"2304.08349","title":"Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach","created":"2023-04-17","cited_by_count":15},{"id":"2308.09175","title":"Diversifying AI: Towards Creative Chess with AlphaZero","created":"2023-08-17","cited_by_count":15},{"id":"1909.12969","title":"Counterfactual States for Atari Agents via Generative Deep Learning","created":"2019-09-27","cited_by_count":14},{"id":"2211.03769","title":"Are AlphaZero-like Agents Robust to Adversarial Perturbations?","created":"2022-11-07","cited_by_count":14},{"id":"1905.11852","title":"EDUCE: Explaining model Decisions through Unsupervised Concepts Extraction","created":"2019-05-28","cited_by_count":13},{"id":"2001.10284","title":"Distal Explanations for Model-free Explainable Reinforcement Learning","created":"2020-01-28","cited_by_count":12},{"id":"2002.03549","title":"Adversarial TCAV -- Robust and Effective Interpretation of Intermediate Layers in Neural Networks","created":"2020-02-10","cited_by_count":12},{"id":"1902.03129","title":"Towards Automatic Concept-based Explanations","created":"2019-02-07","cited_by_count":11},{"id":"2203.11547","title":"Explainability in reinforcement learning: perspective and position","created":"2022-03-22","cited_by_count":11},{"id":"2209.12006","title":"Explainable Reinforcement Learning via Model Transforms","created":"2022-09-24","cited_by_count":11},{"id":"1809.06064","title":"Object-sensitive Deep Reinforcement Learning","created":"2018-09-17","cited_by_count":10},{"id":"1809.09369","title":"S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning","created":"2018-09-25","cited_by_count":6},{"id":"2005.06223","title":"DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics","created":"2020-05-13","cited_by_count":5},{"id":"2204.07531","title":"Understanding Game-Playing Agents with Natural Language Annotations","created":"2022-04-15","cited_by_count":3},{"id":"2206.09046","title":"Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis","created":"2022-06-17","cited_by_count":3},{"id":"2309.01458","title":"Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning","created":"2023-09-04","cited_by_count":3},{"id":"1606.07112","title":"Visualizing Dynamics: from t-SNE to SEMI-MDPs","created":"2016-06-22","cited_by_count":2},{"id":"2307.13192","title":"Counterfactual Explanation Policies in RL","created":"2023-07-25","cited_by_count":2}],"next_cursor":null}