Related papers: Distributionally Robust Free Energy Principle for …
The next generation of autonomous agents must not only learn efficiently but also act reliably and adapt their behavior in open worlds. Standard approaches typically assume fixed tasks and environments with little or no novelty, which…
Reinforcement learning (RL) is a powerful technique for training intelligent agents, but understanding why these agents make specific decisions can be quite challenging. This lack of transparency in RL models has been a long-standing…
Flexible, goal-directed behavior is a fundamental aspect of human life. Based on the free energy minimization principle, the theory of active inference formalizes the generation of such behavior from a computational neuroscience…
Model-Based Reinforcement Learning involves learning a \textit{dynamics model} from data, and then using this model to optimise behaviour, most often with an online \textit{planner}. Much of the recent research along these lines presents a…
Model-based reinforcement learning promises to learn an optimal policy from fewer interactions with the environment compared to model-free reinforcement learning by learning an intermediate model of the environment in order to predict…
Self-interested individuals often fail to cooperate, posing a fundamental challenge for multi-agent learning. How can we achieve cooperation among self-interested, independent learning agents? Promising recent work has shown that in certain…
An autonomous and resilient controller is proposed for leader-follower multi-agent systems under uncertainties and cyber-physical attacks. The leader is assumed non-autonomous with a nonzero control input, which allows changing the team…
Shared autonomy is an operational concept in which a user and an autonomous agent collaboratively control a robotic system. It provides a number of advantages over the extremes of full-teleoperation and full-autonomy in many settings.…
One major obstacle that precludes the success of reinforcement learning in real-world applications is the lack of robustness, either to model uncertainties or external disturbances, of the trained policies. Robustness is critical when the…
We present a variational free-energy formulation for distributionally robust decision-making with ambiguity in the generative model. The formulation, related to a broad range of learning and control frameworks, yields a minimax optimal…
In humans, perceptual awareness facilitates the fast recognition and extraction of information from sensory input. This awareness largely depends on how the human agent interacts with the environment. In this work, we propose active neural…
We study a multi-agent output regulation problem, where not all agents have access to the exosystem's dynamics. We propose a fully distributed controller that solves the problem for linear, heterogeneous, and uncertain agent dynamics as…
The COVID-19 pandemic brings many unexpected disruptions, such as frequently shifting markets and limited human workforce, to manufacturers. To stay competitive, flexible and real-time manufacturing decision-making strategies are needed to…
Active inference is a theory of perception, learning and decision making, which can be applied to neuroscience, robotics, and machine learning. Recently, reasearch has been taking place to scale up this framework using Monte-Carlo tree…
A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and…
In multi-agent safety-critical scenarios, traditional autonomous driving frameworks face significant challenges in balancing safety constraints and task performance. These frameworks struggle to quantify dynamic interaction risks in…
We consider repeated allocation of a shared resource via a non-monetary mechanism, wherein a single item must be allocated to one of multiple agents in each round. We assume that each agent has i.i.d. values for the item across rounds, and…
We seek to clarify the concept of active inference by disentangling it from the Free Energy Principle. We show how the optimizations that need to be carried out in order to implement active inference in discrete state spaces can be…
Following the pivotal success of learning strategies to win at tasks, solely by interacting with an environment without any supervision, agents have gained the ability to make sequential decisions in complex MDPs. Yet, reinforcement…
Recently, there has been increasing interest in transparency and interpretability in Deep Reinforcement Learning (DRL) systems. Verbal explanations, as the most natural way of communication in our daily life, deserve more attention, since…