Related papers: Climate Change Policy Exploration using Reinforcem…
Robotic shepherding problem considers the control and navigation of a group of coherent agents (e.g., a flock of bird or a fleet of drones) through the motion of an external robot, called shepherd. Machine learning based methods have…
Climate change is one of the defining challenges of the 21st century, and many in the robotics community are looking for ways to contribute. This paper presents a roadmap for climate-relevant robotics research, identifying high-impact…
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group…
Recent years have seen significant advancements in designing reinforcement learning (RL)-based agents for building energy management. While individual success is observed in simulated or controlled environments, the scalability of RL…
This paper seeks to establish a framework for directing a society of simple, specialized, self-interested agents to solve what traditionally are posed as monolithic single-agent sequential decision problems. What makes it challenging to use…
Autonomous navigation is challenging for mobile robots, especially in an unknown environment. Commonly, the robot requires multiple sensors to map the environment, locate itself, and make a plan to reach the target. However, reinforcement…
In lifelong learning, an agent learns throughout its entire life without resets, in a constantly changing environment, as we humans do. Consequently, lifelong learning comes with a plethora of research problems such as continual domain…
Reinforcement learning (RL) systems can be complex and non-interpretable, making it challenging for non-AI experts to understand or intervene in their decisions. This is due in part to the sequential nature of RL in which actions are chosen…
Energy system models underpin decisions by energy system planners and operators. Energy system modelling faces a transformation: accounting for changing meteorological conditions imposed by climate change. To enable that transformation, a…
Several complicated non-linear models exist which simulate the physical processes leading to fluctuations in global climate. Some of these more advanced models use observations to constrain various parameters involved. However, they tend to…
Trading markets represent a real-world financial application to deploy reinforcement learning agents, however, they carry hard fundamental challenges such as high variance and costly exploration. Moreover, markets are inherently a…
Many sequential decision-making problems that are currently automated, such as those in manufacturing or recommender systems, operate in an environment where there is either little uncertainty, or zero risk of catastrophe. As companies and…
We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…
The climate system is a forced, dissipative, nonlinear, complex and heterogeneous system that is out of thermodynamic equilibrium. The system exhibits natural variability on many scales of motion, in time as well as space, and it is subject…
Reinforcement learning agents have demonstrated remarkable achievements in simulated environments. Data efficiency poses an impediment to carrying this success over to real environments. The design of data-efficient agents calls for a…
Being able to reason in an environment with a large number of discrete actions is essential to bringing reinforcement learning to a larger class of problems. Recommender systems, industrial plants and language models are only some of the…
A self-learning adaptive system (SLAS) uses machine learning to enable and enhance its adaptability. Such systems are expected to perform well in dynamic situations. For learning high-performance adaptation policy, some assumptions must be…
A central challenge in climate science and applied mathematics is developing data-driven models of multiscale systems that capture both stationary statistics and responses to external perturbations. Current neural climate emulators aim to…
We explore how physical scale and population size shape the emergence of complex behaviors in open-ended ecological environments. In our setting, agents are unsupervised and have no explicit rewards or learning objectives but instead evolve…
One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…