Implementations of the algorithms described in Munos, R. (2014). From bandits to Monte-Carlo Tree Search: The optimistic principle applied to optimization and planning. Foundations and Trends® in Machine Learning, 7(1), 1-129.
The algorithms are implemented only for finding the maximum of a function defined on [0, 1].
Algorithms implemented:
- Section 3: Optimistic optimization with known smoothness
- Deterministic Optimistic Optimization (DOO)
- Stochastic Optimistic Optimization (StoOO)
- Hierarchical Optimistic Optimization (HOO)
- Section 4: Simultaneous Optimistic Optimization
- Simultaneous Optimistic Optimization (SOO)
- Stochastic Simultaneous Optimistic Optimization (StoSOO)
Algorithms to implement:
- Section 5: Optimistic planning
- Optimistic Planning algorithm (OPD)
- Open Loop Optimistic Planning (OLOP)
- Optimistic planning in MDP (OP-MDP)
Requirements:
- Python 3.7
- Numpy 1.14
- Networkx 2.1
