Related papers: Ask-AC: An Initiative Advisor-in-the-Loop Actor-Cr…

Action advising is a peer-to-peer knowledge exchange technique built on the teacher-student paradigm to alleviate the sample inefficiency problem in deep reinforcement learning. Recently proposed student-initiated approaches have obtained…

In practice, imitation learning is preferred over pure reinforcement learning whenever it is possible to design a teaching agent to provide expert supervision. However, we show that when the teaching agent makes decisions with access to…

As large language models (LLMs) show increasing promise on research-level physics reasoning tasks and agentic AI becomes more common, a practical question emerges: How does the interaction between researchers and agents affect the results?…

Multi-agent social dilemmas, such as the tragedy of the commons, capture settings where individual incentives conflict with collective well-being, making these systems highly vulnerable to collapse under disruptions. In this context, this…

Imitation learning aims to mimic the behavior of experts without explicit reward signals. Passive imitation learning methods which use static expert datasets typically suffer from compounding error, low sample efficiency, and high…

Actor-critic algorithms address the dual goals of reinforcement learning (RL), policy evaluation and improvement via two separate function approximators. The practicality of this approach comes at the expense of training instability, caused…

Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contrast successful actions against suboptimal alternatives and…

We introduce a general-purpose, human-in-the-loop dual dialogue system to support mental health care professionals. The system, co-designed with care providers, is conceptualized to assist them in interacting with care seekers rather than…

This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on…

Robotic imitation learning has advanced from solving static tasks to addressing dynamic interaction scenarios, but testing and evaluation remain costly and challenging due to the need for real-time interaction with dynamic environments. We…

Multi-agent reinforcement learning is difficult to be applied in practice, which is partially due to the gap between the simulated and real-world scenarios. One reason for the gap is that the simulated systems always assume that the agents…

This paper presents a novel approach combining inductive logic programming with reinforcement learning to improve training performance and explainability. We exploit inductive learning of answer set programs from noisy examples to learn a…

Multi-agent systems often operate under feedback, adaptation, and non-stationarity, yet many simulation studies retain static decision rules and fixed control parameters. This paper introduces a general adaptive multi-agent learning…

The primary goal of this study is to analyze agentic workflows in education according to the proposed four major technological paradigms: reflection, planning, tool use, and multi-agent collaboration. We critically examine the role of AI…

We consider the dynamic multichannel access problem, which can be formulated as a partially observable Markov decision process (POMDP). We first propose a model-free actor-critic deep reinforcement learning based framework to explore the…

In open systems, i.e. systems operating in an environment that they cannot control and with components that may join or leave, behaviors can arise as side effects of intensive components interaction. Finding ways to understand and design…

Large-scale industrial recommenders typically use a fixed multi-stage pipeline (recall, ranking, re-ranking) and have progressed from collaborative filtering to deep and large pre-trained models. However, both multi-stage and so-called One…

Reinforcement learning has gathered much attention in recent years due to its rapid development and rich applications, especially on control systems and robotics. When tackling real-world applications with reinforcement learning method, the…

Language agents have become a promising solution to complex interactive tasks. One of the key ingredients to the success of language agents is the reward model on the trajectory of the agentic workflow, which provides valuable guidance…

Autonomous agents operating in continuous environments must decide not only what to do, but when to act. We introduce a lightweight adaptive temporal control system that learns the optimal interval between cognitive ticks from experience,…