{"total":45,"rows":[{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190,"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":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63,"area":null},{"id":"2303.01859","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","created":"2023-03-03","cited_by_count":62,"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":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36,"area":null},{"id":"2206.03446","title":"Learning in Observable POMDPs, without Computationally Intractable Oracles","created":"2022-06-07","cited_by_count":30,"area":null},{"id":"2211.01991","title":"Leveraging Fully Observable Policies for Learning under Partial Observability","created":"2022-11-03","cited_by_count":18,"area":null},{"id":"2309.14970","title":"Recurrent Hypernetworks are Surprisingly Strong in Meta-RL","created":"2023-09-26","cited_by_count":16,"area":null},{"id":"2306.02418","title":"ContraBAR: Contrastive Bayes-Adaptive Deep RL","created":"2023-06-04","cited_by_count":9,"area":null},{"id":"2310.04128","title":"Reinforcement Learning with Fast and Forgetful Memory","created":"2023-10-06","cited_by_count":9,"area":null},{"id":"2206.03597","title":"Meta-Learning Parameterized Skills","created":"2022-06-07","cited_by_count":7,"area":null},{"id":"2302.07350","title":"Graph schemas as abstractions for transfer learning, inference, and planning","created":"2023-02-14","cited_by_count":7,"area":null},{"id":"2309.14078","title":"ODE-based Recurrent Model-free Reinforcement Learning for POMDPs","created":"2023-09-25","cited_by_count":7,"area":null},{"id":"2310.18144","title":"Improving Intrinsic Exploration by Creating Stationary Objectives","created":"2023-10-27","cited_by_count":7,"area":null},{"id":"2408.08770","title":"Pessimistic Iterative Planning with RNNs for Robust POMDPs","created":"2024-08-16","cited_by_count":7,"area":null},{"id":"2204.01437","title":"Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning","created":"2022-04-04","cited_by_count":6,"area":null},{"id":"2311.04830","title":"Real-Time Recurrent Reinforcement Learning","created":"2023-11-08","cited_by_count":6,"area":null},{"id":"2402.06783","title":"Learn to Teach: Sample-Efficient Privileged Learning for Humanoid Locomotion over Diverse Terrains","created":"2024-02-09","cited_by_count":6,"area":null},{"id":"2210.01422","title":"Time-Varying Propensity Score to Bridge the Gap between the Past and Present","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2308.05937","title":"A Deep Recurrent-Reinforcement Learning Method for Intelligent AutoScaling of Serverless Functions","created":"2023-08-11","cited_by_count":5,"area":null},{"id":"2303.10623","title":"Active hypothesis testing in unknown environments using recurrent neural networks and model free reinforcement learning","created":"2023-03-19","cited_by_count":4,"area":null},{"id":"2304.05008","title":"Habits and goals in synergy: a variational Bayesian framework for behavior","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2307.05891","title":"PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks","created":"2023-07-12","cited_by_count":4,"area":null},{"id":"2312.05332","title":"MPC-Inspired Reinforcement Learning for Verifiable Model-Free Control","created":"2023-12-08","cited_by_count":3,"area":null},{"id":"2404.15597","title":"GRSN: Gated Recurrent Spiking Neurons for POMDPs and MARL","created":"2024-04-24","cited_by_count":3,"area":null},{"id":"2410.08355","title":"Metalic: Meta-Learning In-Context with Protein Language Models","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2411.02975","title":"Transformer-Based Fault-Tolerant Control for Fixed-Wing UAVs Using Knowledge Distillation and In-Context Adaptation","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2512.19154","title":"Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2306.12314","title":"Introspective Action Advising for Interpretable Transfer Learning","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2404.09715","title":"Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2607.27132","title":"Minimal Markovization via Stable Quotients in Holonomy-Cover Decision Processes","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2304.10246","title":"Filter-Aware Model-Predictive Control","created":"2023-04-20","cited_by_count":1,"area":null},{"id":"2307.15931","title":"Robust Recurrent Reinforcement Learning under Evolving Hidden Disturbances with Application to Rover Wheel Slip","created":"2023-07-29","cited_by_count":1,"area":null},{"id":"2508.09960","title":"GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2306.15909","title":"RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2312.12973","title":"Sparse Mean Field Load Balancing in Large Localized Queueing Systems","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2407.11456","title":"Graceful task adaptation with a bi-hemispheric RL agent","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2512.15824","title":"State-Augmented Graphs for Circular Economy Triage","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2605.05373","title":"Hidden States as Value Gradients: The Pontryagin Structure of Recurrent Policies","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.17431","title":"MATE: Solving Contextual Markov Decision Processes with Memory of Accumulated Transition Embeddings","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.18820","title":"When to Commit and When to Defer: Maturing Markov Decision Processes under Refining Information and Expiring Opportunities","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.11445","title":"Event-based Neural Decoding for Neuroprosthetic Motor Control","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.11953","title":"When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.08644","title":"Path-dependent Discrete Amortized Inference","created":"2026-08-09","cited_by_count":0,"area":null}],"next_cursor":null}