arXiv:2512. 22560v2 Announce Type: replace-cross Abstract: Agentic Reinforcement Learning (RL) trains LLMs through multi-turn interactions with environments, producing workloads that mix compute-bound prefill, bandwidth-bound decoding, CPU-heavy environment execution, and bursty reward evaluation.
arXiv:2609.24456v1 Announce Type: cross Abstract: Distributed reinforcement learning (RL) scales training by parallelizing actors and learners around an Experience Buffer. As RL workloads grow, howev...
ReFlow is a system‑algorithm co‑designed framework for efficient reinforcement learning (RL) post‑training of large language models (LLMs). It introduces replay‑driven decoupling, allowing recent trajectories to be reused multiple times to amortize rollout costs while limiting policy staleness. The architecture features a dual replay cycle, an elastic resource pool, and an adaptive scheduler, achieving up to 2.06× higher training throughput compared to existing synchronous and asynchronous RL systems without sacrificing model performance.
arXiv:2605. 26418v2 Announce Type: replace-cross Abstract: A properly calibrated rule-based autoscaler can beat every one of six mainstream deep reinforcement learning (DRL) algorithms on cost across every workload we test - so when, if ever, does DRL actually help?
arXiv:2604.19146v2 Announce Type: replace Abstract: Particle accelerator beamline optimization is a high-dimensional control problem traditionally requiring significant expert intervention. We presen...
arXiv:2606. 24340v1 Announce Type: new Abstract: In recent years, the Internet of Things (IoT) paradigm has been shifting toward batteryless, energy-harvesting architectures.
arXiv:2609.13243v1 Announce Type: cross Abstract: We present GzDRL, a novel single-process reinforcement learning (RL) framework for Gazebo that overcomes longstanding bottlenecks in scalable, reprod...
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:2507. 04136v2 Announce Type: replace Abstract: This survey offers a comprehensive foundation on the integration of RL with language models, highlighting prominent algorithms such as Proximal Policy Optimization (PPO), Q-Learning, and Actor-Critic methods.
In recent years, the Internet of Things (IoT) paradigm has been shifting toward batteryless, energy-harvesting architectures. Sustaining reliable operation in these systems requires intelligent management of highly volatile stored energy.
arXiv:2608. 26418v1 Announce Type: cross Abstract: Modern AI workloads and the hardware that runs them evolve on different timescales: architectural definition precedes volume silicon by years, while target workloads shift in months.
arXiv:2511. 07046v4 Announce Type: replace-cross Abstract: Deploying continuous-control reinforcement learning policies on embedded hardware requires meeting tight latency and power budgets.