Sumários

P3: Learning and Decision-Making + Architectures

4 novembro 2022, 09:30 • Alberto Vale

  • Presentations of work progress Learning and Decision-Making + Architectures
  • Rehearsal of the final presentation

Decision-Making IV

3 novembro 2022, 08:00 • Pedro Urbano Lima

Examples of robot systems using Reinforcement learning and MDPs.

Architectures for robot systems: functional (hierarchical, heterarchical, hybrid), software and hardware.

Decision-Making III

31 outubro 2022, 08:00 • Pedro Urbano Lima

Solving MDPs using Dynamic Programming.

Reinforcement Learning. TD-learning. Q-Learning. SARSA. Exploration vs Exploitation.

P3: Learning and Decision-Making

28 outubro 2022, 09:30 • Alberto Vale

  • Presentations of work progress about Decision-Making
  • Support to students

Decision-Making II

27 outubro 2022, 08:00 • Pedro Urbano Lima

Predicate logic. Situation Calculus. STRIPS. PDDL.

Introduction to Markov Decision Processes. Planning under uncertainty as solving an MDP.