Sumários
Learning
5 Maio 2023, 15:00 • Luis Manuel Ferreira Fernandes Moniz
Run the examples of Q-Learning and MCTS
Exercises
- Run the Q-Learning example.
- Change the reward function in (1) to solve the Cab example in the figure
- Run the example tictactoe in MCTS file package executing this file
- Implement another game example to use MCTS (for instance Ultimate tic tac toe)
Learning in games
5 Maio 2023, 13:00 • Luis Manuel Ferreira Fernandes Moniz
| Learning concepts applied to games. Bayes classifiers. Decision trees. Reinforcement learning. Neural Networks. Monte Carlo Tree Search. Application examples. |
Planning
28 Abril 2023, 16:30 • Luis Manuel Ferreira Fernandes Moniz
Use of a planner "Planner" in several planning problems (python 3).
Objective
Using the planner, define several domains and build some planning problems.
Exercises
- Run the zenotravel example with several scheduling issues.
- Run the sokoban example with several scheduling issues.
- Define the planning problem corresponding to the sokoban example from the class slides and find the plan to solve it.
- Modify the planning domain to have a bot that can push two blocks.
Planning
28 Abril 2023, 15:00 • Luis Manuel Ferreira Fernandes Moniz
Use of a planner "Planner" in several planning problems (python 3).
Objective
Using the planner, define several domains and build some planning problems.
Exercises
- Run the zenotravel example with several scheduling issues.
- Run the sokoban example with several scheduling issues.
- Define the planning problem corresponding to the sokoban example from the class slides and find the plan to solve it.
- Modify the planning domain to have a bot that can push two blocks.
Planning in games
28 Abril 2023, 13:00 • Luis Manuel Ferreira Fernandes Moniz
| Introduction to game planning. Basic concepts. Classical planning algorithms, search in state space. Neoclassical algorithms, search in the space of planes, POP and PNP algorithms. Planning Graphs. Hierarchical planning, HTN algorithms. |