Improve B_k attacks

[pkel]

The $B_k$ protocol has some hard-coded attack strategies but they are not nearly optimal. Consider this graph from https://github.com/pkel/cpr/blob/training/experiments/rl-eval/compare-models-and-find-breakeven.ipynb.

Two ways forward:

1. Copy/adapt the best hard-coded policy against tailstorm and check how it performs
2. Try to reverse-engineer the learned policies.

[pkel]

Addressed in #40. I chose option 1 above.