{"total":152,"rows":[{"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":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200,"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":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2303.07507","title":"Loss of Plasticity in Continual Deep Reinforcement Learning","created":"2023-03-13","cited_by_count":121,"area":null},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90,"area":null},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86,"area":null},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73,"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":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57,"area":null},{"id":"2304.01315","title":"Empirical Design in Reinforcement Learning","created":"2023-04-03","cited_by_count":55,"area":null},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","created":"2021-07-02","cited_by_count":53,"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":"2106.04615","title":"Vector Quantized Models for Planning","created":"2021-06-08","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":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45,"area":null},{"id":"2502.07825","title":"Pre-Trained Video Generative Models as World Simulators","created":"2025-02-10","cited_by_count":44,"area":null},{"id":"2106.08229","title":"MICo: Improved representations via sampling-based state similarity for Markov decision processes","created":"2021-06-03","cited_by_count":43,"area":null},{"id":"2106.09678","title":"SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies","created":"2021-06-17","cited_by_count":43,"area":null},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2312.03801","title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","created":"2023-12-06","cited_by_count":39,"area":null},{"id":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","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":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"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":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2302.09465","title":"Stochastic Generative Flow Networks","created":"2023-02-19","cited_by_count":32,"area":null},{"id":"2301.04462","title":"An Analysis of Quantile Temporal-Difference Learning","created":"2023-01-11","cited_by_count":31,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"area":null},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2306.03186","title":"Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning","created":"2023-06-05","cited_by_count":28,"area":null},{"id":"2102.04399","title":"How to Stay Curious while Avoiding Noisy TVs using Aleatoric Uncertainty Estimation","created":"2021-02-08","cited_by_count":27,"area":null},{"id":"2210.01542","title":"Hyperbolic Deep Reinforcement Learning","created":"2022-10-04","cited_by_count":25,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2103.06469","title":"Generalizable Episodic Memory for Deep Reinforcement Learning","created":"2021-03-11","cited_by_count":23,"area":null},{"id":"2107.05431","title":"CoBERL: Contrastive BERT for Reinforcement Learning","created":"2021-07-12","cited_by_count":21,"area":null},{"id":"2110.02102","title":"CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning","created":"2021-10-05","cited_by_count":21,"area":null},{"id":"2110.10735","title":"Dynamic Bottleneck for Robust Self-Supervised Exploration","created":"2021-10-20","cited_by_count":21,"area":null},{"id":"2108.11811","title":"When should agents explore?","created":"2021-08-26","cited_by_count":20,"area":null},{"id":"2103.11883","title":"Regularized Softmax Deep Multi-Agent $Q$-Learning","created":"2021-03-22","cited_by_count":19,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2206.03271","title":"On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning","created":"2022-06-07","cited_by_count":19,"area":null},{"id":"2203.11203","title":"Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approach","created":"2022-03-19","cited_by_count":17,"area":null},{"id":"2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","created":"2022-08-25","cited_by_count":15,"area":null},{"id":"2101.08153","title":"Shielding Atari Games with Bounded Prescience","created":"2021-01-20","cited_by_count":14,"area":null},{"id":"2110.01528","title":"Large Batch Experience Replay","created":"2021-10-04","cited_by_count":14,"area":null},{"id":"2206.08353","title":"Towards Understanding How Machines Can Learn Causal Overhypotheses","created":"2022-06-16","cited_by_count":14,"area":null},{"id":"2305.05239","title":"Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection","created":"2023-05-09","cited_by_count":14,"area":null},{"id":"2305.18388","title":"The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation","created":"2023-05-28","cited_by_count":14,"area":null},{"id":"2310.11305","title":"MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13,"area":null},{"id":"2106.03955","title":"Correcting Momentum in Temporal Difference Learning","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2112.04145","title":"A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutions","created":"2021-12-08","cited_by_count":12,"area":null},{"id":"2206.03192","title":"Generalized Data Distribution Iteration","created":"2022-06-07","cited_by_count":12,"area":null},{"id":"2302.05326","title":"Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks","created":"2023-01-20","cited_by_count":11,"area":null},{"id":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","cited_by_count":11,"area":null},{"id":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","cited_by_count":10,"area":null},{"id":"2111.10247","title":"Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari","created":"2021-11-19","cited_by_count":10,"area":null},{"id":"2301.12579","title":"Sample Efficient Deep Reinforcement Learning via Local Planning","created":"2023-01-29","cited_by_count":10,"area":null},{"id":"2306.02419","title":"Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL","created":"2023-06-04","cited_by_count":10,"area":null},{"id":"2110.03184","title":"Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2204.06355","title":"Local Feature Swapping for Generalization in Reinforcement Learning","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2207.08389","title":"MLGOPerf: An ML Guided Inliner to Optimize Performance","created":"2022-07-18","cited_by_count":9,"area":null},{"id":"2305.01521","title":"Unlocking the Power of Representations in Long-term Novelty-based Exploration","created":"2023-05-02","cited_by_count":9,"area":null},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2106.15419","title":"Convergent and Efficient Deep Q Network Algorithm","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2110.00535","title":"A Cram\\'er Distance perspective on Quantile Regression based Distributional Reinforcement Learning","created":"2021-10-01","cited_by_count":8,"area":null},{"id":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2112.05848","title":"Faster Deep Reinforcement Learning with Slower Online Network","created":"2021-12-10","cited_by_count":7,"area":null},{"id":"2202.10430","title":"Learning Causal Overhypotheses through Exploration in Children and Computational Models","created":"2022-02-21","cited_by_count":7,"area":null},{"id":"2310.00036","title":"Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform","created":"2023-09-29","cited_by_count":7,"area":null},{"id":"2310.17805","title":"Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2105.07582","title":"RAIDER: Reinforcement-aided Spear Phishing Detector","created":"2021-05-17","cited_by_count":6,"area":null},{"id":"2106.10365","title":"Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments","created":"2021-06-18","cited_by_count":6,"area":null},{"id":"2107.01348","title":"Examining average and discounted reward optimality criteria in reinforcement learning","created":"2021-07-03","cited_by_count":6,"area":null},{"id":"2110.15331","title":"Wasserstein Distance Maximizing Intrinsic Control","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2209.14218","title":"DMAP: a Distributed Morphological Attention Policy for Learning to Locomote with a Changing Body","created":"2022-09-28","cited_by_count":6,"area":null},{"id":"2305.15277","title":"Successor-Predecessor Intrinsic Exploration","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2307.03486","title":"Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2404.07817","title":"Calibration of Continual Learning Models","created":"2024-04-11","cited_by_count":6,"area":null},{"id":"2111.01100","title":"Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2208.14928","title":"Cell-Free Latent Go-Explore","created":"2022-08-31","cited_by_count":5,"area":null},{"id":"2306.10404","title":"The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions","created":"2023-06-17","cited_by_count":5,"area":null},{"id":"2308.00707","title":"Approximate Model-Based Shielding for Safe Reinforcement Learning","created":"2023-07-27","cited_by_count":5,"area":null},{"id":"2410.23810","title":"CALE: Continuous Arcade Learning Environment","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2203.07171","title":"Orchestrated Value Mapping for Reinforcement Learning","created":"2022-03-14","cited_by_count":4,"area":null},{"id":"2210.12448","title":"Probing Transfer in Deep Reinforcement Learning without Task Engineering","created":"2022-10-22","cited_by_count":4,"area":null},{"id":"2211.10515","title":"Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments","created":"2022-11-18","cited_by_count":4,"area":null}],"next_cursor":"100"}