Contents
- 16.1 Overview
- 16.2 Software Agents
- 16.2.1 The Rise of the Agent
- 16.2.2 Triggering Actions
- 16.2.3 Watching and Learning
- 16.2.4 Searching for Information
- 16.3 Reinforcement Learning
- 16.3.1 Single Step Learning
- 16.3.2 Choices during Learning
- 16.3.3 Intermittent Rewards and Credit Assignment
- 16.4 Co-operating Agents and Distributed AI
- 16.4.1 Blackboard Architectures
- 16.4.2 Distributed Control
- 16.5 Larger Collectives
- 16.5.1 Emergent Behaviour
- 16.5.2 Cellular Automata
- 16.5.3 Artificial Life
- 16.5.4 Swarm Computing
- 16.5.5 Ensemble Methods
- 16.6 Summary
Glossary items referenced in this chapter
agents, agents!action, agents!email filtering, agents!embodied, agents!intelligent filtering, agents!machine learning, agents!messages, agents!methods, artificial life, artificial society, Bayesian methods, bibliographic database, bibliographic search, blackboard architecture, boosting, cellular automata, Clippy, computer chess, concept learning, Conway, John, cooperating agents, cost–benefit, counterfactual reasoning, credit assignment, database, decision tree, DeepSeek, deterministic, distributed AI, distributed cognition, EAGER, emergent behaviour, ensemble methods, ensemble methods!heterogeneous, ensemble methods!homogeneous, event, exploration-exploitation trade-off, flocking behaviour, Game of Life, Google, Google alerts, heuristic evaluation function, home automation, Human Computer Interaction, hypertext, IFTTT , image processing, immune system, intermittent rewards, internet of things, knowledge base, large language model, local maximum, machine learning, macro languages, mixture-of-experts, network routing, neural network, NewWave, object-oriented architecture, object-oriented programming, observation–action mapping, obstacle avoidance, optimal route, overfitting, PageRank, Pavlov, Ivan, Pogoing robots, pole balancing, prisoner's dilemma, privacy, programming-by-demonstration, random forest, regret, reinforcement learning, reservoir computing, robotic process automation, robotics, robotics!practical, route planning, script, search engine, self-organising map, similarity measure, single step learning, Skinner, B. F., social media, status change event, stemming, strong learner, supervised learning, support vector machine, swarm computing, system event, timed event, trigger, unsupervised learning, user event, user interface agent, weak learners, wisdom of the crowds, wizard, World Wide Web
Prolog examples (from 1st ed.)
| blackboard.p | blackboard architecture |
| life.p | Conways game of Life |