Advanced Topics in Computational Intelligence

• Weekly hours
• Competences
• Objectives
• Contents
• Activities
• Teaching methodology
• Evaluation methodology
• Bibliography
• Web links
• Previous capacities

Teachers

Person in charge

• Mario Martín Muñoz ( )

Weekly hours

Competences

Generic Technical Competences

Generic

• CG3 - Capacity for modeling, calculation, simulation, development and implementation in technology and company engineering centers, particularly in research, development and innovation in all areas related to Artificial Intelligence.
• CG4 - Capacity for general management, technical management and research projects management, development and innovation in companies and technology centers in the area of Artificial Intelligence.

Technical Competences of each Specialization

Academic

• CEA3 - Capability to understand the basic operation principles of Machine Learning main techniques, and to know how to use on the environment of an intelligent system or service.
• CEA9 - Capability to understand Multiagent Systems advanced techniques, and to know how to design, implement and apply these techniques in the development of intelligent applications, services or systems.
• CEA11 - Capability to understand the advanced techniques of Computational Intelligence, and to know how to design, implement and apply these techniques in the development of intelligent applications, services or systems.

Professional

• CEP2 - Capability to solve the decision making problems from different organizations, integrating intelligent tools.
• CEP3 - Capacity for applying Artificial Intelligence techniques in technological and industrial environments to improve quality and productivity.
• CEP8 - Capability to respect the surrounding environment and design and develop sustainable intelligent systems.

Transversal Competences

Teamwork

• CT3 - Ability to work as a member of an interdisciplinary team, as a normal member or performing direction tasks, in order to develop projects with pragmatism and sense of responsibility, making commitments taking into account the available resources.

Objectives

1. To understand the need, fundamentals, and particularities of behavior learning and the differences it has from supervised and unsupervised machine learning.
   Related competences: CEA11, CEA3, CG3, CG4,
2. To distinguish the kind of problems can be modeled as a reinforcement learning problem and identify the techniques that can be applied to solve them.
   Related competences: CEA11, CEA3, CEP2, CEP3,
3. To understand the most important algorithms and state of the art in the area of learning by reinforcement
   Related competences: CEA11, CEA3, CG3, CG4,
4. To know how to computationally formalize a real world problem as learning by reinforcement and know how to implement in the most current environments the learning algorithms that solve them
   Related competences: CT3, CEP2, CEP3, CEP8, CG4,
5. To understand the most advanced and recent techniques in the field of Multi-Agent learning to cooperate and compete.
   Related competences: CT3, CEA9, CEP2, CEP3, CEP8, CG4,
6. To understand the difficulties and inefficiencies of the reinforcement learning approach and propose the techniques and approaches that could solve them
   Related competences: CEA11, CEP3, CEP8, CG3, CG4,

Contents

1. Introduction: Behavior Learning in Agents and description of main elements in Reinforcement Learning
   Intuition, motivation and definition of the reinforcement learning (RL) framework. Key elements in RL.
2. Finding optimal policies using Dynamic Programming
   How to learn the optimal policy with full knowledge of the world model: algebraic solution, policy iteration and value iteration.
3. Introduction to Model-Free approaches.
   Basic algorithms for reinforcement learning: Monte-Carlo, Q-learning, Sarsa, TD(lambda). The need for Exploration. Differences between On-policy and Off-policy methods.
4. Function approximation in Reinforcement Learning
   Need for function approximation and Incremental methods in RL. The Gradient Descent approach. RL with Linear function approximation. The deadly triad for function approximation in RL. Batch methods and Neural Networks for function Approximation.
5. Deep Reinforcement Learning (DRL)
   Revolution in RL by introducing Deep Learning. Dealing with the deadly triad with the DQN algorithm. Application to the Atari games case. Evolutions of the DQN algorithm: Double DQN, Prioritized Experience Replay, multi-step learning and Distributional value functions. Rainbow: the state-of-the-art algorithm in discrete action space.
6. Advanced topics: Model Based Reinforcement Learning (MBRL)
   Separating the learning of the policy from the learning of a model of the world has some benefits and some problems. Sample efficiency in RL by hallucination and imagination.
7. Policy gradient methods
   What to do in continuous action spaces. How probabilistic policies allow to apply the gradient method directly in the policy network. The REINFORCE algorithm. The Actor-Critic algorithms. State-of-the-art algorithms in continuous action spaces: DDPG, TD3 and SAC.
8. Advanced Topics: How to deal with sparse rewards
   The problem of the sparse reward. Introduction to advanced exploration techniques: curiosity and empowerment in RL. Introduction to curriculum learning to easy the learning of the goal. Hierarchical RL to learn complex tasks. The learning of Universal Value Functions and Hindsight Experience Replay (HER).
9. Advanced Topics: Towards Long-life learning in agents
   Is RL a way to obtain a General Artificial Intelligence? Multi-task learning in RL, Transfer learning in RL and Meta-learning in RL. State-of-the-art approaches.
10. Reinforcement Learning in the multi-agent framework
    Learning of behaviors in environment where several agents act. Learning of cooperative behaviors, Learning of competitive behaviors, and mixed cases. State-of-the art algorithms. The special case of games: The AlfaGo case and the extension to Alfa-Zero.

Activities

Activity Evaluation act

Teaching methodology

Evaluation methodology

Bibliography

Basic:

• Reinforcement learning : an introduction - Sutton, Richard S; Barto, Andrew G, The MIT Press, [2018]. ISBN: 9780262039246
  https://discovery.upc.edu/discovery/fulldisplay?docid=alma991004166329706711&context=L&vid=34CSUC_UPC:VU1&lang=ca
• Deep reinforcement learning - Morales, M, Manning Publications, 2020. ISBN: 9781617295454
  https://discovery.upc.edu/discovery/fulldisplay?docid=alma991004208939706711&context=L&vid=34CSUC_UPC:VU1&lang=ca

Complementary:

• Deep reinforcement learning in action - Zai, A.; Brown, B, Manning Publications Co. , 2020. ISBN: 9781617295430
  https://discovery.upc.edu/discovery/fulldisplay?docid=alma991004203829706711&context=L&vid=34CSUC_UPC:VU1&lang=ca

Web links

• Master in Artificial Intelligence http://www.fib.upc.edu/en/masters/mai.html
• Web page of the course with all materials. https://www.cs.upc.edu/~mmartin/ATCI-RL.html

Previous capacities