Exploration, Exploitation and Model Learning
A handbook for balancing learning and performance in uncertain decision systems using bandit logic, model-based learning, model-free learning and controlled exploration.
Every page in the KEVOS library tagged reinforcement learning. 4 pages.
A handbook for balancing learning and performance in uncertain decision systems using bandit logic, model-based learning, model-free learning and controlled exploration.
A practical guide to directly optimising decision policies using parameterised policy search, gradient estimation, actor-critic architectures and stable optimisation practices.
Choose among supervised, unsupervised and reinforcement learning by matching the learning signal, decision structure and available evidence to the business task.
A risk-focused field guide to deciding well under uncertainty: 26 chapters across five parts, from probabilistic reasoning to multiagent systems, re-read for the project profess…