{"total":458,"rows":[{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817,"area":null},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"area":null},{"id":"2405.14573","title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","created":"2024-05-23","cited_by_count":468,"area":null},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371,"area":null},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366,"area":null},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288,"area":null},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219,"area":null},{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201,"area":null},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174,"area":null},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163,"area":null},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2203.11931","title":"MetaMorph: Learning Universal Controllers with Transformers","created":"2022-03-22","cited_by_count":89,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2403.07059","title":"Better than classical? The subtle art of benchmarking quantum machine learning models","created":"2024-03-11","cited_by_count":85,"area":null},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2103.02142","title":"Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control","created":"2021-03-03","cited_by_count":77,"area":null},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65,"area":null},{"id":"2303.01859","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","created":"2023-03-03","cited_by_count":62,"area":null},{"id":"2311.17295","title":"Elo Uncovered: Robustness and Best Practices in Language Model Evaluation","created":"2023-11-29","cited_by_count":61,"area":null},{"id":"2102.13651","title":"On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning","created":"2021-02-26","cited_by_count":59,"area":null},{"id":"2106.11872","title":"Randomness In Neural Network Training: Characterizing The Impact of Tooling","created":"2021-06-22","cited_by_count":59,"area":null},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59,"area":null},{"id":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57,"area":null},{"id":"2111.00607","title":"A Systematic Investigation of Commonsense Knowledge in Large Language Models","created":"2021-10-31","cited_by_count":56,"area":null},{"id":"2301.00557","title":"Learning to Maximize Mutual Information for Dynamic Feature Selection","created":"2023-01-02","cited_by_count":56,"area":null},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55,"area":null},{"id":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2109.06325","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49,"area":null},{"id":"2103.04514","title":"Nondeterminism and Instability in Neural Network Optimization","created":"2021-03-08","cited_by_count":48,"area":null},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46,"area":null},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2410.11905","title":"A Scalable Communication Protocol for Networks of Large Language Models","created":"2024-10-14","cited_by_count":45,"area":null},{"id":"2201.08430","title":"Reproducibility in Learning","created":"2022-01-20","cited_by_count":44,"area":null},{"id":"2106.02940","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","created":"2021-06-05","cited_by_count":43,"area":null},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2111.00072","title":"Generalized Proximal Policy Optimization with Sample Reuse","created":"2021-10-29","cited_by_count":40,"area":null},{"id":"2509.03493","title":"On Entropy Control in LLM-RL Algorithms","created":"2025-09-03","cited_by_count":40,"area":null},{"id":"2205.13881","title":"Automated Dynamic Algorithm Configuration","created":"2022-05-27","cited_by_count":39,"area":null},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2109.11052","title":"On Bonus-Based Exploration Methods in the Arcade Learning Environment","created":"2021-09-22","cited_by_count":37,"area":null},{"id":"2103.05115","title":"Deep reinforcement learning in medical imaging: A literature review","created":"2021-03-05","cited_by_count":34,"area":null},{"id":"2109.09180","title":"Lifelong Robotic Reinforcement Learning by Retaining Experiences","created":"2021-09-19","cited_by_count":34,"area":null},{"id":"2209.09203","title":"Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning","created":"2022-09-16","cited_by_count":34,"area":null},{"id":"2201.12417","title":"Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error","created":"2022-01-28","cited_by_count":32,"area":null},{"id":"2204.07610","title":"Sources of Irreproducibility in Machine Learning: A Review","created":"2022-04-15","cited_by_count":32,"area":null},{"id":"2101.02808","title":"Average-Reward Off-Policy Policy Evaluation with Function Approximation","created":"2021-01-08","cited_by_count":31,"area":null},{"id":"2102.10264","title":"On Proximal Policy Optimization's Heavy-tailed Gradients","created":"2021-02-20","cited_by_count":31,"area":null},{"id":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31,"area":null},{"id":"2202.01331","title":"Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions","created":"2022-02-02","cited_by_count":31,"area":null},{"id":"2210.12089","title":"A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges","created":"2022-10-21","cited_by_count":30,"area":null},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"area":null},{"id":"2102.03349","title":"On the Reproducibility of Neural Network Predictions","created":"2021-02-05","cited_by_count":29,"area":null},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2110.03331","title":"CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability","created":"2021-10-07","cited_by_count":28,"area":null},{"id":"2110.11222","title":"Is High Variance Unavoidable in RL? A Case Study in Continuous Control","created":"2021-10-21","cited_by_count":28,"area":null},{"id":"2204.06815","title":"deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks","created":"2022-04-14","cited_by_count":28,"area":null},{"id":"2201.01666","title":"Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation","created":"2022-01-05","cited_by_count":27,"area":null},{"id":"2310.19796","title":"Re-evaluating Retrosynthesis Algorithms with Syntheseus","created":"2023-10-30","cited_by_count":27,"area":null},{"id":"2102.10536","title":"Learning Efficient Navigation in Vortical Flow Fields","created":"2021-02-21","cited_by_count":26,"area":null},{"id":"2202.10583","title":"MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned","created":"2022-02-17","cited_by_count":26,"area":null},{"id":"2110.01307","title":"Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning with Shapley Values","created":"2021-10-04","cited_by_count":25,"area":null},{"id":"2111.07775","title":"Learning Representations for Pixel-based Control: What Matters and Why?","created":"2021-11-15","cited_by_count":24,"area":null},{"id":"2209.02606","title":"Unifying Generative Models with GFlowNets and Beyond","created":"2022-09-06","cited_by_count":24,"area":null},{"id":"2102.09407","title":"Adaptive Rational Activations to Boost Deep Reinforcement Learning","created":"2021-02-18","cited_by_count":23,"area":null},{"id":"2202.02326","title":"Towards Training Reproducible Deep Learning Models","created":"2022-02-04","cited_by_count":23,"area":null},{"id":"2401.11849","title":"Self-Labeling the Job Shop Scheduling Problem","created":"2024-01-22","cited_by_count":23,"area":null},{"id":"2210.01898","title":"Replicable Bandits","created":"2022-10-04","cited_by_count":22,"area":null},{"id":"2212.11110","title":"Lifelong Reinforcement Learning with Modulating Masks","created":"2022-12-21","cited_by_count":22,"area":null},{"id":"2108.07555","title":"Revisiting State Augmentation methods for Reinforcement Learning with Stochastic Delays","created":"2021-08-17","cited_by_count":21,"area":null},{"id":"2109.14830","title":"Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators","created":"2021-09-30","cited_by_count":21,"area":null},{"id":"2305.15284","title":"Replicable Reinforcement Learning","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2305.19562","title":"Replicability in Reinforcement Learning","created":"2023-05-31","cited_by_count":21,"area":null},{"id":"2306.03301","title":"Estimating Conditional Mutual Information for Dynamic Feature Selection","created":"2023-06-05","cited_by_count":21,"area":null},{"id":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","cited_by_count":20,"area":null},{"id":"2102.03034","title":"Hyperparameter Optimization Is Deceiving Us, and How to Stop It","created":"2021-02-05","cited_by_count":20,"area":null},{"id":"2112.03850","title":"Policy Search for Model Predictive Control with Application to Agile Drone Flight","created":"2021-12-07","cited_by_count":20,"area":null},{"id":"2207.09405","title":"Bayesian Generational Population-Based Training","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2209.00532","title":"Actor Prioritized Experience Replay","created":"2022-09-01","cited_by_count":20,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2108.01005","title":"Sequoia: A Software Framework to Unify Continual Learning Research","created":"2021-08-02","cited_by_count":19,"area":null},{"id":"2405.02200","title":"Position: Why We Must Rethink Empirical Research in Machine Learning","created":"2024-05-03","cited_by_count":19,"area":null},{"id":"2101.10276","title":"Emergent Communication under Competition","created":"2021-01-25","cited_by_count":18,"area":null},{"id":"2108.03319","title":"Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learning","created":"2021-08-06","cited_by_count":18,"area":null},{"id":"2110.15572","title":"Understanding the Effect of Stochasticity in Policy Optimization","created":"2021-10-29","cited_by_count":18,"area":null},{"id":"2204.10817","title":"Reward Reports for Reinforcement Learning","created":"2022-04-22","cited_by_count":18,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null}],"next_cursor":"100"}