Hierarchical policy learning is a method in machine learning where a complex task is divided into smaller, simpler tasks, each managed by its own policy or set of rules. These smaller policies are organised in a hierarchy, with higher-level policies deciding which lower-level policies to use at any moment. This structure helps break down difficult…
Category: Autonomous Systems
Augmented Reality Workflows
Augmented Reality (AR) workflows are processes that combine digital information or graphics with the real world, allowing users to interact with both at the same time. These workflows often use smartphones, tablets or specialised glasses to overlay virtual guides, instructions or visual data onto physical objects and spaces. By doing this, AR workflows help people…
Spiking Neural Networks
Spiking Neural Networks, or SNNs, are a type of artificial neural network designed to work more like the human brain. They process information using spikes, which are brief electrical pulses, rather than continuous signals. This makes them more energy efficient and suitable for certain tasks. SNNs are particularly good at handling data that changes over…
Neuromorphic Computing
Neuromorphic computing is a type of technology that tries to mimic the way the human brain works by designing computer hardware and software that operates more like networks of neurons. Instead of following traditional computer architecture, neuromorphic systems use structures that process information in parallel and can adapt based on experience. This approach aims to…
Sim-to-Real Transfer
Sim-to-Real Transfer is a technique in robotics and artificial intelligence where systems are trained in computer simulations and then adapted for use in the real world. The goal is to use the speed, safety, and cost-effectiveness of simulations to develop skills or strategies that can work outside the virtual environment. This process requires addressing differences…
Domain Randomisation
Domain randomisation is a technique used in artificial intelligence, especially in robotics and computer vision, to make models more robust. It involves exposing a model to many different simulated environments where aspects like lighting, textures, and object positions are changed randomly. By training on these varied scenarios, the model learns to perform well even when…
Competitive Multi-Agent Systems
Competitive multi-agent systems are computer-based environments where multiple independent agents interact with each other, often with opposing goals. Each agent tries to achieve its own objectives, which may conflict with the objectives of others. These systems are used to study behaviours such as competition, negotiation, and strategy among agents. They are commonly applied in areas…
Cooperative Game Theory in AI
Cooperative game theory in AI studies how multiple intelligent agents can work together to achieve shared goals or maximise collective benefits. It focuses on strategies for forming alliances, dividing rewards, and making group decisions fairly and efficiently. This approach helps AI systems collaborate, negotiate, and coordinate actions in environments where working together is more effective…
Multi-Agent Reinforcement Learning
Multi-Agent Reinforcement Learning (MARL) is a field of artificial intelligence where multiple agents learn to make decisions by interacting with each other and their environment. Each agent aims to maximise its own rewards, which can lead to cooperation, competition, or a mix of both, depending on the context. MARL extends standard reinforcement learning by introducing…
Model-Based Reinforcement Learning
Model-Based Reinforcement Learning is a branch of artificial intelligence where an agent learns not only by trial and error but also by building an internal model of how its environment works. This model helps the agent predict the outcomes of its actions before actually trying them, making learning more efficient. By simulating possible scenarios, the…