The paper introduces the first strategyproof deep reinforcement learning mechanism for online resource allocation, combining a monotonic neural network, a generalized critical payment rule, and training via RL or imitation. This design ensures truthful reporting and individual rationality while capturing nonlinear resource interactions beyond linear models. Experiments on a four‑resource stream show the neural rule attains 97.8% of an offline welfare upper bound, outperforming linear learners and first‑come, first‑served baselines, and imitation training achieves comparable performance 89 times faster than RL.
Online resource allocation faces two coupled challenges: (1) allocating scarce resources efficiently under uncertain future demand, and (2) ensuring that agents report task valuations and requirements...
arXiv:2602. 05999v3 Announce Type: replace Abstract: How does the amount of compute available to a reinforcement learning (RL) policy affect its learning?
arXiv:2606. 09825v1 Announce Type: cross Abstract: Training reinforcement learning (RL) policies from scratch is costly: it requires careful reward and environment design, extensive tuning, and substantial computation.
arXiv:2507. 09473v2 Announce Type: replace-cross Abstract: We study the dynamic allocation of indivisible resources to strategic agents under long-term constraints, where the planner aims to maximize social welfare, satisfy multiple constraints, and elicit near-truthful reports.
The paper introduces ProAS, a Progress‑Aware Advantage Shaping framework designed to improve critic‑free reinforcement learning for large language model agents. ProAS uses a dynamic Agentic Reference Graph to provide fine‑grained credit assignment through Masking Unreasonable Incentives and Asymmetric Penalty Redistribution, avoiding the uniform advantage broadcast that can reinforce invalid actions. Experiments on Qwen2.5‑1.5B‑Instruct and Qwen2.5‑7B‑Instruct show that ProAS raises baseline success rates to 91.9% and 94.3% on ALFWorld and 66.7% and 70.8% on WebShop, while speeding up training convergence up to 2.44× and remaining robust to imperfect reference graphs.
Reinforcement learning (RL) has emerged as the primary paradigm for optimizing Large Language Model (LLM) agents, yet efficient critic-free algorithms (e.g., GRPO) suffer from a fundamental uniform cr...
arXiv:2607. 13389v1 Announce Type: new Abstract: Reinforcement Learning (RL) post-training is increasingly used to adapt foundation models for reasoning, planning, and feedback-driven robot-learning pipelines, but constrained post-training resources are often summarized by a single total FLOP budget.
arXiv:2606. 20008v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become a central tool for improving the reasoning ability of large language models, but current methods face a trade-off between simplicity and credit assignment.
arXiv:2609.36393v1 Announce Type: cross Abstract: Traditional reinforcement learning (RL) techniques focus on maximizing expected cumulative reward, where each action assumes to take a constant unit...
arXiv:2607. 07435v1 Announce Type: cross Abstract: Agents acting on our behalf in the real world (e.
arXiv:2608.20909v1 Announce Type: new Abstract: Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled l...
arXiv:2503. 07869v4 Announce Type: replace Abstract: Critical learning periods (CLPs) in federated learning (FL) refer to early stages during which low-quality contributions (e.