{"total":82,"rows":[{"id":"2205.11491","title":"HyperTree Proof Search for Neural Theorem Proving","created":"2022-05-23","cited_by_count":197,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"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":"2208.07860","title":"A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning","created":"2022-08-16","cited_by_count":83,"area":"wm"},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2206.07638","title":"Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays","created":"2022-06-15","cited_by_count":63,"area":null},{"id":"2104.06272","title":"Podracer architectures for scalable Reinforcement Learning","created":"2021-04-13","cited_by_count":38,"area":null},{"id":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30,"area":"lr"},{"id":"2503.18929","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","created":"2025-03-24","cited_by_count":29,"area":"lr"},{"id":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2103.04972","title":"Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation","created":"2021-03-08","cited_by_count":23,"area":null},{"id":"2106.07551","title":"MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning","created":"2021-06-05","cited_by_count":23,"area":null},{"id":"2203.12759","title":"Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots","created":"2022-03-23","cited_by_count":22,"area":null},{"id":"2407.20230","title":"SAPG: Split and Aggregate Policy Gradients","created":"2024-07-29","cited_by_count":21,"area":"deeprl"},{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2206.13477","title":"Parametrically Retargetable Decision-Makers Tend To Seek Power","created":"2022-06-27","cited_by_count":19,"area":null},{"id":"2512.23075","title":"Trust Region Masking for Long-Horizon LLM Reinforcement Learning","created":"2025-12-28","cited_by_count":16,"area":null},{"id":"2202.05195","title":"Uncovering Instabilities in Variational-Quantum Deep Q-Networks","created":"2022-02-10","cited_by_count":14,"area":null},{"id":"2210.02317","title":"Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","cited_by_count":11,"area":"deeprl"},{"id":"2102.10740","title":"Communication Efficient Parallel Reinforcement Learning","created":"2021-02-22","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":"2206.05060","title":"Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENS","created":"2022-06-10","cited_by_count":10,"area":null},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2103.04067","title":"Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning","created":"2021-03-06","cited_by_count":9,"area":null},{"id":"2103.14496","title":"Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation","created":"2021-03-26","cited_by_count":9,"area":"distill"},{"id":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9,"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":"2411.05614","title":"Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey","created":"2024-11-08","cited_by_count":8,"area":"deeprl"},{"id":"2502.08123","title":"Provably Robust Federated Reinforcement Learning","created":"2025-02-12","cited_by_count":8,"area":"deeprl"},{"id":"2112.05848","title":"Faster Deep Reinforcement Learning with Slower Online Network","created":"2021-12-10","cited_by_count":7,"area":null},{"id":"2103.00683","title":"Decision Making in Monopoly using a Hybrid Deep Reinforcement Learning Approach","created":"2021-03-01","cited_by_count":6,"area":null},{"id":"2301.11135","title":"FedHQL: Federated Heterogeneous Q-Learning","created":"2023-01-26","cited_by_count":6,"area":null},{"id":"2102.04285","title":"RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads","created":"2021-02-08","cited_by_count":5,"area":null},{"id":"2306.07552","title":"Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2212.00253","title":"Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox","created":"2022-12-01","cited_by_count":4,"area":null},{"id":"2408.08628","title":"A survey on secure decentralized optimization and learning","created":"2024-08-16","cited_by_count":4,"area":null},{"id":"2305.10978","title":"Client Selection for Federated Policy Optimization with Environment Heterogeneity","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2306.06251","title":"Design Principles for Model Generalization and Scalable AI Integration in Radio Access Networks","created":"2023-06-09","cited_by_count":3,"area":null},{"id":"2309.04615","title":"VDFD: Multi-Agent Value Decomposition Framework with Disentangled World Model","created":"2023-09-08","cited_by_count":3,"area":"wm"},{"id":"2309.16743","title":"High Throughput Training of Deep Surrogates from Large Ensemble Runs","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2408.09237","title":"QEDCartographer: Automating Formal Verification Using Reward-Free Reinforcement Learning","created":"2024-08-17","cited_by_count":3,"area":"deeprl"},{"id":"2507.06602","title":"Generalization in Reinforcement Learning for Radio Access Networks","created":"2025-07-09","cited_by_count":3,"area":"deeprl"},{"id":"2511.21011","title":"Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning","created":"2025-11-26","cited_by_count":3,"area":"deeprl"},{"id":"2101.02308","title":"Coding for Distributed Multi-Agent Reinforcement Learning","created":"2021-01-07","cited_by_count":2,"area":null},{"id":"2110.01101","title":"Parallel Actors and Learners: A Framework for Generating Scalable RL Implementations","created":"2021-10-03","cited_by_count":2,"area":null},{"id":"2205.15891","title":"One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning","created":"2022-05-31","cited_by_count":2,"area":null},{"id":"2209.09329","title":"MAN: Multi-Action Networks Learning","created":"2022-09-19","cited_by_count":2,"area":null},{"id":"2211.13260","title":"Actively Learning Costly Reward Functions for Reinforcement Learning","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2308.12438","title":"Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2402.07890","title":"MAIDCRL: Semi-centralized Multi-Agent Influence Dense-CNN Reinforcement Learning","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2506.06410","title":"Delphos: A reinforcement learning framework for assisting discrete choice model specification","created":"2025-06-06","cited_by_count":2,"area":"deeprl"},{"id":"2509.01793","title":"STORI: A Benchmark and Taxonomy for Stochastic Environments","created":"2025-09-01","cited_by_count":2,"area":"deeprl"},{"id":"2110.08169","title":"Containerized Distributed Value-Based Multi-Agent Reinforcement Learning","created":"2021-10-15","cited_by_count":1,"area":null},{"id":"2111.07631","title":"AI in Human-computer Gaming: Techniques, Challenges and Opportunities","created":"2021-11-15","cited_by_count":1,"area":null},{"id":"2202.05135","title":"Group-Agent Reinforcement Learning","created":"2022-02-10","cited_by_count":1,"area":null},{"id":"2210.02882","title":"Scaling up Stochastic Gradient Descent for Non-convex Optimisation","created":"2022-10-06","cited_by_count":1,"area":null},{"id":"2402.06682","title":"Private Knowledge Sharing in Distributed Learning: A Survey","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2506.22075","title":"Reasoning in machine vision by learning fast and slow thinking","created":"2025-06-27","cited_by_count":1,"area":"lr"},{"id":"2107.00481","title":"Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge Industrial IoT","created":"2021-06-30","cited_by_count":0,"area":null},{"id":"2107.14457","title":"Maximum Entropy Dueling Network Architecture in Atari Domain","created":"2021-07-30","cited_by_count":0,"area":null},{"id":"2108.02128","title":"Parallelized Reverse Curriculum Generation","created":"2021-08-04","cited_by_count":0,"area":null},{"id":"2109.01417","title":"Event-Based Communication in Distributed Q-Learning","created":"2021-09-03","cited_by_count":0,"area":null},{"id":"2110.13506","title":"Accelerating Distributed Deep Reinforcement Learning by In-Network Experience Sampling","created":"2021-10-26","cited_by_count":0,"area":null},{"id":"2111.01264","title":"Human-Level Control without Server-Grade Hardware","created":"2021-11-01","cited_by_count":0,"area":null},{"id":"2202.09019","title":"Distributed Multi-Agent Reinforcement Learning with One-hop Neighbors and Compute Straggler Mitigation","created":"2022-02-18","cited_by_count":0,"area":null},{"id":"2205.09543","title":"Parallel bandit architecture based on laser chaos for reinforcement learning","created":"2022-05-19","cited_by_count":0,"area":null},{"id":"2210.12896","title":"Classifying Ambiguous Identities in Hidden-Role Stochastic Games with Multi-Agent Reinforcement Learning","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2211.04119","title":"Simulation-Based Parallel Training","created":"2022-11-08","cited_by_count":0,"area":null},{"id":"2305.18501","title":"DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2306.04846","title":"Learned spatial data partitioning","created":"2023-06-08","cited_by_count":0,"area":null},{"id":"2307.05232","title":"A Survey From Distributed Machine Learning to Distributed Deep Learning","created":"2023-07-11","cited_by_count":0,"area":null},{"id":"2307.12983","title":"Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation","created":"2023-07-24","cited_by_count":0,"area":null},{"id":"2412.12700","title":"ParMod: A Parallel and Modular Framework for Learning Non-Markovian Tasks","created":"2024-12-17","cited_by_count":0,"area":"deeprl"},{"id":"2502.20190","title":"Highly Parallelized Reinforcement Learning Training with Relaxed Assignment Dependencies","created":"2025-02-27","cited_by_count":0,"area":"deeprl"},{"id":"2503.14554","title":"Synchronous vs Asynchronous Reinforcement Learning in a Real World Robot","created":"2025-03-17","cited_by_count":0,"area":"deeprl"},{"id":"2507.10990","title":"Adaptive Policy Synchronization for Scalable Reinforcement Learning","created":"2025-07-15","cited_by_count":0,"area":"deeprl"},{"id":"2607.17326","title":"Rethinking the Suitability of Reinforcement Learning Algorithms Under Practical Transfer Constraints","created":"2026-07-19","cited_by_count":0,"area":"deeprl"},{"id":"2609.22888","title":"Stable and Efficient Real-World Online VLA Post-Training via Asynchronous Replay-Anchored Policy Improvement","created":"2026-09-19","cited_by_count":0,"area":"vla"},{"id":"2609.25463","title":"Rollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directions","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2610.04196","title":"Asynchronous Is Nearly Free for Evolution Strategies on Long-Horizon Agentic Tasks","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.10273","title":"A Closed-Loop Non-Asymptotic Convergence Analysis of PPO with Learned Critics and Clipping","created":"2026-10-07","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}