Related papers: Causality Meets Locality: Provably Generalizable a…
Multi-Agent Reinforcement Learning (MARL) has emerged as a foundational approach for addressing diverse, intelligent control tasks in various scenarios like the Internet of Vehicles, Internet of Things, and Unmanned Aerial Vehicles.…
We study causal representation learning, the task of recovering high-level latent variables and their causal relationships in the form of a causal graph from low-level observed data (such as text and images), assuming access to observations…
We propose a new policy iteration theory as an important extension of soft policy iteration and Soft Actor-Critic (SAC), one of the most efficient model free algorithms for deep reinforcement learning. Supported by the new theory, arbitrary…
In many problems, the measured variables (e.g., image pixels) are just mathematical functions of the latent causal variables (e.g., the underlying concepts or objects). For the purpose of making predictions in changing environments or…
Domain generalization aims at developing suitable learning algorithms in source training domains such that the model learned can generalize well on a different unseen testing domain. We present a novel two-stage approach called…
Real-world problems, for example in climate applications, often require causal reasoning on spatially gridded time series data or data with comparable structure. While the underlying system is often believed to behave similarly at different…
We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally occurring spurious correlations, which cause them to fail on…
This paper focuses on causal representation learning (CRL) under a general nonparametric latent causal model and a general transformation model that maps the latent data to the observational data. It establishes identifiability and…
Multi-agent deep reinforcement learning makes optimal decisions dependent on system states observed by agents, but any uncertainty on the observations may mislead agents to take wrong actions. The Mean-Field Actor-Critic reinforcement…
Representation learning is a central challenge across a range of machine learning areas. In reinforcement learning, effective and functional representations have the potential to tremendously accelerate learning progress and solve more…
Causal inference is crucial for humans to explore the world, which can be modeled to enable an agent to efficiently explore the environment in reinforcement learning. Existing research indicates that establishing the causality between…
Large language model (LLM) agents -- LLMs that dynamically interact with an environment over long horizons -- have become an increasingly important area of research, enabling automation in complex tasks involving tool-use, web browsing, and…
Although Reinforcement Learning (RL) is effective for sequential decision-making problems under uncertainty, it still fails to thrive in real-world systems where risk or safety is a binding constraint. In this paper, we formulate the RL…
In this paper, we devise a distributional framework on actor-critic as a solution to distributional instability, action type restriction, and conflation between samples and statistics. We propose a new method that minimizes the Cram\'er…
Scale variation has been a challenge from traditional to modern approaches in computer vision. Most solutions to scale issues have a similar theme: a set of intuitive and manually designed policies that are generic and fixed (e.g. SIFT or…
We address the problem of safe reinforcement learning from pixel observations. Inherent challenges in such settings are (1) a trade-off between reward optimization and adhering to safety constraints, (2) partial observability, and (3)…
This PhD thesis contains several contributions to the field of statistical causal modeling. Statistical causal models are statistical models embedded with causal assumptions that allow for the inference and reasoning about the behavior of…
Cooperative multi-agent reinforcement learning (MARL) aims to develop agents that can collaborate effectively. However, most cooperative MARL methods overfit training agents, making learned policies not generalize well to unseen…
We consider the linear causal representation learning setting where we observe a linear mixing of $d$ unknown latent factors, which follow a linear structural causal model. Recent work has shown that it is possible to recover the latent…
Persistent monitoring of dynamic targets is essential in real-world applications such as disaster response, environmental sensing, and wildlife conservation, where mobile agents must continuously gather information under uncertainty. We…