{"total":269,"rows":[{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"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":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"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":"2403.03950","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL","created":"2024-03-06","cited_by_count":144,"area":"deeprl"},{"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":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111,"area":"offlinerl"},{"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":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90,"area":"offlinerl"},{"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":"2402.16801","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","created":"2024-02-26","cited_by_count":88,"area":"deeprl"},{"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":"2402.08609","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","created":"2024-02-13","cited_by_count":78,"area":"moe"},{"id":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73,"area":null},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73,"area":"offlinerl"},{"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":"2205.15967","title":"You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments","created":"2022-05-31","cited_by_count":63,"area":"offlinerl"},{"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":"2006.13888","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","created":"2020-06-24","cited_by_count":57,"area":"offlinerl"},{"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":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50,"area":"offlinerl"},{"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":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"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":"1907.04543","title":"An Optimistic Perspective on Offline Reinforcement Learning","created":"2019-07-10","cited_by_count":37,"area":"offlinerl"},{"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":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30,"area":"lr"},{"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":"2405.00662","title":"No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO","created":"2024-05-01","cited_by_count":27,"area":"deeprl"},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2505.10819","title":"PoE-World: Compositional World Modeling with Products of Programmatic Experts","created":"2025-05-16","cited_by_count":26,"area":"wm"},{"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":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23,"area":"deeprl"},{"id":"2407.14503","title":"Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification","created":"2024-07-19","cited_by_count":23,"area":"alignment"},{"id":"2010.08920","title":"Average-reward model-free reinforcement learning: a systematic review and literature mapping","created":"2020-10-18","cited_by_count":22,"area":"alignment"},{"id":"2207.10295","title":"Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning","created":"2022-07-21","cited_by_count":22,"area":"offlinerl"},{"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":"2406.17523","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","created":"2024-06-25","cited_by_count":21,"area":"deeprl"},{"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":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2010.08891","title":"DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs","created":"2020-10-18","cited_by_count":16,"area":"offlinerl"},{"id":"2404.19456","title":"A Survey of Imitation Learning Methods, Environments and Metrics","created":"2024-04-30","cited_by_count":16,"area":"offlinerl"},{"id":"2412.04759","title":"REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments","created":"2024-12-06","cited_by_count":16,"area":"rag"},{"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":"2312.01203","title":"Harnessing Discrete Representations For Continual Reinforcement Learning","created":"2023-12-02","cited_by_count":11,"area":"wm"},{"id":"2404.02113","title":"Position: Lifetime tuning is incompatible with continual reinforcement learning","created":"2024-04-02","cited_by_count":11,"area":"deeprl"},{"id":"2506.14811","title":"Self-Composing Policies for Scalable Continual Reinforcement Learning","created":"2025-06-04","cited_by_count":11,"area":"deeprl"},{"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}],"next_cursor":"100"}