Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2607. 11953v1 Announce Type: new Abstract: Does a reinforcement-learning agent that earns high reward represent its task's latent state, or only a reward-correlated shortcut?
arXiv:2607. 12924v1 Announce Type: new Abstract: In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic action and numerical parameters.
arXiv:2607. 12464v1 Announce Type: cross Abstract: When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated samples are equally useful for the downstream task.
arXiv:2607. 11954v1 Announce Type: cross Abstract: Clinical code prediction maps unstructured discharge summaries to ICD-10-CM leaf codes in a large, sparse, and deeply hierarchical label space.
arXiv:2510. 18315v2 Announce Type: replace-cross Abstract: We investigate how embedding dimension affects the emergence of an internal "world model" in a transformer trained with reinforcement learning to perform bubble-sort-style adjacent swaps.
arXiv:2509. 21842v2 Announce Type: replace Abstract: Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools/resources for travel itinerary generation, ensuring an enjoyable user experience.
arXiv:2607. 13028v1 Announce Type: cross Abstract: Training robust autonomous driving agents requires a simulator that is fast enough for reinforcement learning at scale, realistic enough to ground behavior in real-world map structure, and diverse enough to cover the safety-critical long tail that logged data rarely contains.
arXiv:2607. 12962v1 Announce Type: cross Abstract: Frozen small code LLMs are deployed locally, yet the information guiding a retry after a failed attempt is still measured without placebo controls in the self-repair literature.
arXiv:2607. 12480v1 Announce Type: new Abstract: This paper defines TRACE (Typed Reasoning And Commitment Evidence): a typed, versioned schema for recording reasoning traces, a reference procedure for writing records against it, and one operating discipline, no durable state change without a record.
arXiv:2607. 12763v1 Announce Type: cross Abstract: Federated Reinforcement Learning (FedRL) enables coordination of distributed energy resources without sharing raw local data, but standard aggregation methods such as FedAvg do not account for system-level constraints, often leading to unsafe global behavior.
arXiv:2011. 02565v2 Announce Type: replace-cross Abstract: Temporal abstraction allows reinforcement learning agents to represent knowledge and develop strategies over different temporal scales.
arXiv:2509. 24372v3 Announce Type: replace-cross Abstract: Fine-tuning large language models (LLMs) for downstream tasks is an essential stage of modern AI deployment.
arXiv:2604. 09523v2 Announce Type: replace Abstract: Training reinforcement-learning agents for cyber defense requires an environment that reflects the operational setting: noisy, partial observations, several defenders coordinating across a network, and an adaptive adversary realized through self-play.
arXiv:2607. 12640v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards, and Group Relative Policy Optimization (GRPO) in particular, is now run routinely on a supervised checkpoint in the hope of producing a stronger agent.
arXiv:2607. 12856v1 Announce Type: new Abstract: Buildings are expected to shift cooling loads in response to grid conditions.
arXiv:2607. 12861v1 Announce Type: cross Abstract: Multi-agent Reinforcement Learning (MARL) holds great potential for robot swarms, but the black-box nature of neural policies complicates strategic analysis, limiting multi-robot applications.
arXiv:2601. 19624v3 Announce Type: replace-cross Abstract: Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy, causing over-exploration during stable periods and under-exploration after drift, and leaving unanswered the principled question of how exploration intensity should scale with drift magnitude.
arXiv:2607. 12784v1 Announce Type: cross Abstract: Reinforcement Learning has revolutionized the landscape of robotic research, allowing robust learning of complex robotic skills in simulation.
arXiv:2603. 13356v2 Announce Type: replace Abstract: Robust reinforcement learning typically assumes that feedback sources are either globally trustworthy or corrupted within a fixed global budget.
arXiv:2607. 11959v1 Announce Type: new Abstract: Greenhouse reinforcement learning can test climate-control ideas at a speed and scale that is difficult to achieve with crop experiments alone.