AI Planning for Autonomy

The key focus of this subject is the foundations of autonomous agents that reason about action, applying techniques such as automated planning, reinforcement learning, game theory, and their real-world applications. Autonomous agents are active entities that perceive their environment, reason, plan and execute appropriate actions to achieve their goals, in service of their users (the real world, human beings, or other agents). The subject focuses on the foundations that enable agents to reason autonomously about goals & rewards, perception, actions, strategy, and the knowledge of other agents during collaborative task execution, and the ethical impacts of agents with this ability. The programming language used in this subject is Python. No lectures or workshops on Python will be delivered.

• 1Apply theoretical concepts of reasoning about actions to single and multi-agent problems
• 2Be able to analyse, design, and implement automated planning, reinforcement learning, and game theoretic techniques to given problems
• 3Be able to critically evaluate the strengths, weaknesses, and ethical consequences of different approaches for reasoning about action
• 4Be able to critically justify and choose an appropriate technique for different problems in reasoning about action
• 5Communicate technical solutions about automated planning and reinforcement learning