A fair comparison needs a shared evaluation protocol
Saved outputs include 39 successes in 100 Monte Carlo episodes and 200 in 200 Q-learning episodes, under differing conditions.
Compare methods with shared starts, limits, episode counts, and multiple seeds.
Question
Can the available Monte Carlo and Q-learning outputs support a reliable ranking of the methods?
Experiment
The saved Taxi-v3 outputs record successful episodes for Monte Carlo and Q-learning. Seeds and sometimes evaluation counts differ between methods.
Recorded results
| Method | Recorded successes |
|---|---|
| Monte Carlo | 39 / 100 episodes |
| Q-learning | 200 / 200 episodes |
Limits
The implementation labelled “first-visit Monte Carlo” requires correction before a new comparison. The saved counts alone do not establish general performance.
Interpretation
The outputs describe the available runs. Because the evaluation conditions differ, they do not rigorously rank the algorithms.
Compare methods with shared starts, limits, episode counts, and multiple seeds.
Next experiment
Correct the first-visit Monte Carlo implementation, then evaluate both methods from the same initial states, with the same limits and episode counts, over multiple seeds.
Origin & contribution
Educational Taxi-v3 reinforcement-learning project. Counts come from an editorial synthesis of saved notebook outputs supplied for this update; the notebooks are not in this checkout.
The original learning code and precise personal contribution still need source review. The browser Taxi Lab is a separate reference reconstruction, not either trained policy.