Do the right thing: studies in limited rationality
Do the right thing: studies in limited rationality
AI Magazine
The sciences of the artificial (3rd ed.)
The sciences of the artificial (3rd ed.)
The independent choice logic for modelling multiple agents under uncertainty
Artificial Intelligence - Special issue on economic principles of multi-agent systems
Intelligent planning: a decomposition and abstraction based approach
Intelligent planning: a decomposition and abstraction based approach
Computational intelligence: a logical approach
Computational intelligence: a logical approach
Planning and acting in partially observable stochastic domains
Artificial Intelligence
A Machine-Oriented Logic Based on the Resolution Principle
Journal of the ACM (JACM)
A near-optimal polynomial time algorithm for learning in certain classes of stochastic games
Artificial Intelligence
Multiagent learning using a variable learning rate
Artificial Intelligence
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Introduction to Multiagent Systems
Introduction to Multiagent Systems
Neuro-Dynamic Programming
Graphical Models for Game Theory
UAI '01 Proceedings of the 17th Conference in Uncertainty in Artificial Intelligence
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
A polynomial-time algorithm for action-graph games
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Hierarchical reinforcement learning with the MAXQ value function decomposition
Journal of Artificial Intelligence Research
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
First-order probabilistic inference
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Generalizing plans to new environments in relational MDPs
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Distributed planning in hierarchical factored MDPs
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
| Hi-index | 0.00 |
This paper aims to provide a framework for understanding the construction of intelligent agents. This is used to explain the history of AI, and provide a roadmap of future research. Research has progressed by making simplifying assumptions about the representations of the agents or about the environments the agents act in. In particular, we present a number of dimensions of simplifying assumptions that have been made. For each of these dimensions, there is a simplified case and progressively more complex cases. We argue that an intelligent agent needs the complex value in each of these dimensions (i.e., to simultaneously give up many simplifying assumptions). However these dimensions interact in complex ways. Much of the recent history can be seen as understanding the interaction of these dimensions.