相关论文: Learning while Competing -- 3D Modeling & Design

This paper presents a work-in-progress on a learn-ing system that will provide robotics students with a personalized learning environment. This addresses both the scarcity of skilled robotics instructors, particularly in community colleges…

Model-free Reinforcement Learning (RL) works well when experience can be collected cheaply and model-based RL is effective when system dynamics can be modeled accurately. However, both assumptions can be violated in real world problems such…

Learning visuomotor policies for agile quadrotor flight presents significant difficulties, primarily from inefficient policy exploration caused by high-dimensional visual inputs and the need for precise and low-latency control. To address…

Preference-based reinforcement learning (PbRL) is a suitable approach for style adaptation of pre-trained robotic behavior: adapting the robot's policy to follow human user preferences while still being able to perform the original task.…

Mobile robots are essential in applications such as autonomous delivery and hospitality services. Applying learning-based methods to address mobile robot tasks has gained popularity due to its robustness and generalizability. Traditional…

Curiosity as a means to explore during reinforcement learning problems has recently become very popular. However, very little progress has been made in utilizing curiosity for learning control. In this work, we propose a model-based…

We introduce Prompt Curriculum Learning (PCL), a lightweight reinforcement learning (RL) algorithm that selects intermediate-difficulty prompts using a learned value model to post-train language models. Since post-training LLMs via RL…

We propose an active learning architecture for robots, capable of organizing its learning process to achieve a field of complex tasks by learning sequences of motor policies, called Intrinsically Motivated Procedure Babbling (IM-PB). The…

Recently, the academic community has been giving much attention to Cooperative Learning System, a group learning method combined with pedagogy and social psychology. It allows group members to gain knowledge through collaborations and…

Can we make undergraduate engineering education easier and more fun? This research aims to see if we can answer the ambitious question! The digital game-based learning (DGBL) has been found to increase the efficacy of learning when applied…

Accurately modeling robot dynamics is crucial to safe and efficient motion control. In this paper, we develop and apply an iterative learning semi-parametric model, with a neural network, to the task of autonomous racing with a Model…

Recent years, the database committee has attempted to develop automatic database management systems. Although some researches show that the applying AI to data management is a significant and promising direction, there still exists many…

Model-free Reinforcement Learning (RL) offers an attractive approach to learn control policies for high-dimensional systems, but its relatively poor sample complexity often forces training in simulated environments. Even in simulation,…

Effective planning in model-based reinforcement learning (MBRL) and model-predictive control (MPC) relies on the accuracy of the learned dynamics model. In many instances of MBRL and MPC, this model is assumed to be stationary and is…

Continual Learning, also known as Lifelong or Incremental Learning, has recently gained renewed interest among the Artificial Intelligence research community. Recent research efforts have quickly led to the design of novel algorithms able…

In this paper, we study a tracking control problem for linear time-invariant systems, with model parametric uncertainties, under input and states constraints. We apply the idea of modular design introduced in Benosman et al. 2014, to solve…

We present Aryabhata 1.0, a compact 7B parameter math reasoning model optimized for the Indian academic exam, the Joint Entrance Examination (JEE). Despite rapid progress in large language models (LLMs), current models often remain…

We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. Except the simple Behavior Cloning (BC)…

Federated learning promises to revolutionize machine learning by enabling collaborative model training without compromising data privacy. However, practical adaptability can be limited by critical factors, such as the participation dilemma.…

As a CDIO collaborating member, the School of Mechanical and Electrical Engineering of Sheridan maintains a curriculum that is deeply rooted in skills-based learning, experiential learning, and engineering design. To ensure our graduates…