Cs 188 berkeley

This course cs 188 berkeley introduce the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis will be on the statistical and decision-theoretic modeling paradigm. By the end of this course, you will have built autonomous agents that efficiently make decisions in fully informed, partially observable and adversarial settings.

Completed all homeworks, projects, midterms, and finals in 5 weeks. Created different heuristics. Helped pacman agent find shortest path to eat all dots. Created basic reflex agent based on a variety of parameters. Improved agent to use minimax algorithm with alpha-beta pruning. Implemented expectimax for random ghost agents. Improved evaluation function for pacman states.

Cs 188 berkeley

.

Updated belief distribuition of ghost agents based on sequential noise readings and distribution of future ghost agent states. Latest commit.

.

This course will introduce the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis will be on the statistical and decision-theoretic modeling paradigm. By the end of this course, you will have built autonomous agents that efficiently make decisions in fully informed, partially observable and adversarial settings. Your agents will draw inferences in uncertain environments and optimize actions for arbitrary reward structures. Your machine learning algorithms will classify handwritten digits and photographs. The techniques you learn in this course apply to a wide variety of artificial intelligence problems and will serve as the foundation for further study in any application area you choose to pursue. See the syllabus for slides, deadlines, and the lecture schedule.

Cs 188 berkeley

This course will introduce the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis will be on the statistical and decision-theoretic modeling paradigm. By the end of this course, you will have built autonomous agents that efficiently make decisions in fully informed, partially observable and adversarial settings. Your agents will draw inferences in uncertain environments and optimize actions for arbitrary reward structures.

Yee haw gif

Then, used reinforcement learning to approximate Q-Values. The techniques you learn in this course apply to a wide variety of artificial intelligence problems and will serve as the foundation for further study in any application area you choose to pursue. Mini-Contest due Wed, May 4, pm. Applied machine learning to pacman games. Worked with Markov Decision Processes. Advanced Topics 4: AI Ethics [pdf] [pptx]. Project 1 due Thu, Feb 3, pm. Dismiss alert. You signed in with another tab or window. Section 4 Recording Solutions. Implemented expectimax for random ghost agents. Reload to refresh your session. Project 2. Section 2 Recording Solutions.

This course will introduce the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis will be on the statistical and decision-theoretic modeling paradigm.

Finally, implemented joint particle filtering algorithm with multiple reactive ghosts. Section 4 Recording Solutions. Built Q-Learning agent and an Epsilon Greedy agent. Section 2 Recording Solutions. Last commit date. Project 6 due Fri, April 29, pm. Exam Prep 14 Recording Solutions. Implemented expectimax for random ghost agents. Exam Prep 11 Recording Solutions. Then, worked on changing noise and discount parameters to enact different policies. Readings refer to fourth edition of AIMA unless otherwise specified. Exam Prep 2 Recording Solutions. Project 4 due Fri, April 1, pm. Latest commit History 24 Commits. Section 15 Recording Solutions.