CIS 5210 - Module 8 - Reinforcement Learning

This episode explores reinforcement learning and its relationship to MDPs. Also mentioned: exploration v. exploitation, multi-arm bandits, model-free learning, q-learning. Disclosure: This episode was generated using NotebookLM by uploading Professor Chris Callison-Burch's lecture notes and slides.

This episode explores MDPs, covering stochastic environments, transition functions, reward functions, policies, value iteration, policy iteration, expected utility, finite vs. infinite horizons, discount factors, etc. Disclosure: This episode was generated using NotebookLM by uploading Professor Chris Callison-Burch's lecture notes and slides.

This episode explores knowledge-based agents in AI, covering knowledge bases, inference, propositional logic, theorem proving, logical equivalence, resolution, conjunctive normal form (CNF), proof by contradiction, and distributed knowledge representation and reasoning. Disclosure: This episode was generated using NotebookLM by uploading Professor Chris Callison-Burch's lecture notes and slides.

This episode explores constraint satisfaction problems (CSPs), covering variables, domains, constraints, backtracking search, heuristics, forward checking, constraint propagation, and arc consistency. Disclosure: This episode was generated using NotebookLM by uploading Professor Chris Callison-Burch's lecture notes and slides.

This episode explores adversarial search in game-playing AI, covering game formulation, minimax, game trees, evaluation functions, alpha-beta pruning and expectimax. Disclosure: This episode was generated using NotebookLM by uploading Professor Chris Callison-Burch's lecture notes and slides.

This episode explores informed search algorithms in AI, focusing on A* search. Key topics include: Importance of heuristics in guiding searches, and  the role of admissible heuristics and in optimal solutions. Disclosure: This episode was generated using NotebookLM by uploading Professor Chris Callison-Burch's lecture notes and slides.

This episode explores uninformed search algorithms like BFS, DFS, and iterative deepening search.  Disclosure: This episode was generated using NotebookLM.

This episode explores rational agents in AI, covering: Philosophical foundations Historical context Task environments  Disclosure: This episode was generated using NotebookLM.