Related papers: When (and How) to Trust the Expert: Diagnosing Que…
Model-free Reinforcement Learning (RL) generally suffers from poor sample complexity, mostly due to the need to exhaustively explore the state-action space to find well-performing policies. On the other hand, we postulate that expert…
For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-shot generation. We study PPO-trained agents using MiniGrid as core evaluation…
Domain-specific quantitative reasoning remains a major challenge for large language models (LLMs), especially in fields requiring expert knowledge and complex question answering (QA). In this work, we propose Expert Question Decomposition…
Deep Reinforcement Learning (or just "RL") is gaining popularity for industrial and research applications. However, it still suffers from some key limits slowing down its widespread adoption. Its performance is sensitive to initial…
Type 1 Diabetes (T1D) management requires continuous adjustment of insulin and lifestyle behaviors to maintain blood glucose within a safe target range. Although automated insulin delivery (AID) systems have improved glycemic outcomes, many…
Inference-time scaling can amplify reasoning pathologies: sycophancy, rung collapse, and premature certainty. We present RAudit, a diagnostic protocol for auditing LLM reasoning without ground truth access. The key constraint is blindness:…
Continuous-time nonlinear optimal control problems hold great promise in real-world applications. After decades of development, reinforcement learning (RL) has achieved some of the greatest successes as a general nonlinear control design…
Recently, Offline Reinforcement Learning (RL) has achieved remarkable progress with the emergence of various algorithms and datasets. However, these methods usually focus on algorithmic advancements, ignoring that many low-level…
Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert is fixed at decision time. Many modern systems violate this assumption: after selecting an expert,…
Continuous control Deep Reinforcement Learning (RL) approaches are known to suffer from estimation biases, leading to suboptimal policies. This paper introduces innovative methods in RL, focusing on addressing and exploiting estimation…
Legged locomotion has recently achieved remarkable success with the progress of machine learning techniques, especially deep reinforcement learning (RL). Controllers employing neural networks have demonstrated empirical and qualitative…
Complex learning agents are increasingly deployed alongside existing experts, such as human operators or previously trained agents. However, it remains unclear how should learners optimally incorporate certain forms of expert data, which…
Deep reinforcement learning (RL) models, despite their efficiency in learning an optimal policy in static environments, easily loses previously learned knowledge (i.e., catastrophic forgetting). It leads RL models to poor performance in…
Imitation learning (IL) provides a data-driven framework for approximating policies for large-scale combinatorial optimisation problems formulated as sequential decision problems (SDPs), where exact solution methods are computationally…
The ability to effectively reuse prior knowledge is a key requirement when building general and flexible Reinforcement Learning (RL) agents. Skill reuse is one of the most common approaches, but current methods have considerable…
Existing agents for solving tasks such as ML engineering rely on prompting powerful language models. As a result, these agents do not improve with more experience. In this paper, we show that agents backed by weaker models that improve via…
Reinforcement Learning with Verifiable Rewards (RLVR) elicits long chain-of-thought reasoning in large language models (LLMs), but outcome-based rewards lead to coarse-grained advantage estimation. While existing approaches improve RLVR via…
This work theoretically studies a ubiquitous reinforcement learning policy for controlling the canonical model of continuous-time stochastic linear-quadratic systems. We show that randomized certainty equivalent policy addresses the…
Despite impressive results, reinforcement learning (RL) suffers from slow convergence and requires a large variety of tuning strategies. In this paper, we investigate the ability of RL algorithms on simple continuous control tasks. We show…
Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. While reinforcement learning (RL) has been shown to improve performance in this paradigm, its contributions remain…