AgentStudio
CITS3011
Uninformed
Informed
Games
Probability
Trees
MDP
RL
CITS3011 · Intelligent Agents
Visualised
intelligent agents.
Uninformed Search
Compare six ways to explore the same state space, one expansion at a time.
BFS
UCS
DFS
DLS
IDDFS
Bidirectional
Informed Search
Tune heuristic quality and trust, then watch the frontier change shape.
UCS
A*
Weighted A*
Game Search
Propagate utilities, reveal pruning, or grow a search tree one rollout at a time.
Minimax
Alpha-beta
MCTS
Probabilistic Reasoning
Turn uncertain evidence into beliefs and test which variables can influence one another.
Naive Bayes
Bayesian networks
Decision Trees
Build a classifier recursively and see why each information-gain split wins.
Decision Trees
MDP Planning
See values and policies settle as Bellman updates sweep across a sequential decision world.
Value iteration
Policy iteration
Reinforcement Learning
Follow every update as reward reshapes an agent’s behaviour through experience.
TD(0)
Q-learning
SARSA
