Related papers: Causal Coupled Mechanisms: A Control Method with C…

Online reinforcement learning (RL) algorithms are often difficult to deploy in complex human-facing applications as they may learn slowly and have poor early performance. To address this, we introduce a practical algorithm for incorporating…

Within the context of autonomous driving a model-based reinforcement learning algorithm is proposed for the design of neural network-parameterized controllers. Classical model-based control methods, which include sampling- and lattice-based…

Modern approaches to autonomous driving rely heavily on learned components trained with large amounts of human driving data via imitation learning. However, these methods require large amounts of expensive data collection and even then face…

The building thermodynamics model, which predicts real-time indoor temperature changes under potential HVAC (Heating, Ventilation, and Air Conditioning) control operations, is crucial for optimizing HVAC control in buildings. While…

Reinforcement learning (RL) algorithms struggle with learning optimal policies for tasks where reward feedback is sparse and depends on a complex sequence of events in the environment. Probabilistic reward machines (PRMs) are finite-state…

Exploration and credit assignment under sparse rewards are still challenging problems. We argue that these challenges arise in part due to the intrinsic rigidity of operating at the level of actions. Actions can precisely define how to…

Large Language Models (LLMs) have demonstrated strong performance across a wide range of tasks, yet they still struggle with complex mathematical reasoning, a challenge fundamentally rooted in deep structural dependencies. To address this…

Recently, collaborative robots have begun to train humans to achieve complex tasks, and the mutual information exchange between them can lead to successful robot-human collaborations. In this paper we demonstrate the application and…

What is the role of real-time control and learning in the formation of social conventions? To answer this question, we propose a computational model that matches human behavioral data in a social decision-making game that was analyzed both…

Manipulation tasks can often be decomposed into multiple subtasks performed in parallel, e.g., sliding an object to a goal pose while maintaining contact with a table. Individual subtasks can be achieved by task-axis controllers defined…

This study considers that the collective route choices of travelers en route represent a resolution of their competition on network routes. Well understanding this competition and coordinating their route choices help mitigate urban traffic…

A reflection of our ultimate understanding of a complex system is our ability to control its behavior. Typically, control has multiple prerequisites: It requires an accurate map of the network that governs the interactions between the…

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…

Goal-conditioned hierarchical reinforcement learning (HRL) presents a promising approach for enabling effective exploration in complex, long-horizon reinforcement learning (RL) tasks through temporal abstraction. Empirically, heightened…

Reinforcement learning (RL) has demonstrated remarkable potential in robotic manipulation but faces challenges in sample inefficiency and lack of interpretability, limiting its applicability in real world scenarios. Enabling the agent to…

In this work, we propose a distributed hierarchical locomotion control strategy for whole-body cooperation and demonstrate the potential for migration into large numbers of agents. Our method utilizes a hierarchical structure to break down…

Causal representation learning (CRL) enhances machine learning models' robustness and generalizability by learning structural causal models associated with data-generating processes. We focus on a family of CRL methods that uses contrastive…

Many traditional algorithms for solving combinatorial optimization problems involve using hand-crafted heuristics that sequentially construct a solution. Such heuristics are designed by domain experts and may often be suboptimal due to the…

Human-AI shared control allows human to interact and collaborate with AI to accomplish control tasks in complex environments. Previous Reinforcement Learning (RL) methods attempt the goal-conditioned design to achieve human-controllable…

Optimization of resource distribution has been a challenging topic in current society. To explore this topic, we develop a Coalition Control Model(CCM) based on the Model Predictive Control(MPC) and test it using a fishing model with linear…