PART 1
0/3Q-Table Setup
Initialize the tabular value store and basic lookups over states and actions.
Q-Learning on FrozenLake
Q-Learning on FrozenLake
Train a tabular Q-learning agent with epsilon-greedy exploration and greedy evaluation.
Every source step is its own lesson with intuition, concepts, correctly rendered MathJax mathematics, implementation, tests, mistakes, and a checkpoint.
PART 2
0/4Epsilon-Greedy Action Selection
Implement exploration vs exploitation using random sampling and epsilon decay.
PART 3
0/3Q-Learning Update Rule
Compute TD targets, errors, and apply the Q-learning update to table entries.
PART 4
0/3Training Loop
Combine action selection, environment stepping, and updates into episodes and full training runs.
PART 5
0/3Policy Extraction and Evaluation
Derive a greedy policy from the trained Q-table and measure its success rate on FrozenLake.