Research on Adaptive Mutations

The idea is to adapt mutations during optimizations process, so that mutation probabilities would help in faster and better convergence.

Each mutation can be considered as *Action* in certain *State* (graph or node context) with certain *Reward*. This perspective opens several possibilities of multi-armed bandit formulation and RL formulation of adaptive mutations.

Subissues:
- [ ] #39
- [x] #41
- [x] #42
- [x] #77
- [ ] #43
- [ ] #98

Following is also useful:
- [x] #38
- [x] #83