|
libmcts
A Monte Carlo Tree Search Library
|
selector that selects the childnode, that maximises the ratio between samples and ev of the parent node. More...
#include <uct_selector.hpp>
Public Member Functions | |
| UCTSelector (double _C) | |
| constructs a new selector More... | |
| double | evaluate (node_t *node) const |
| this function has to be implemented in derived classes that specializes the metric to be used. every child is evaluated against this method. More... | |
Public Member Functions inherited from mcts::MaxFunctionSelector< Context, Config > | |
| node_t * | select (node_t *node) |
| select a child of node More... | |
Additional Inherited Members | |
Public Types inherited from mcts::ISelectionStrategy< Context, Config > | |
| typedef ISelectionStrategy< Context, Config > | sstrategy_t |
selector that selects the childnode, that maximises the ratio between samples and ev of the parent node.
| Context | @README |
| Config | @README |
Definition at line 18 of file uct_selector.hpp.
|
inline |
constructs a new selector
| _C | Exploration vs Exploitation small C = tree will be expanded deeper, the best node will be evaluated often. big C = the tree will be expanded wider.More nodes in one level will be evaluated. |
Definition at line 35 of file uct_selector.hpp.
|
inlinevirtual |
this function has to be implemented in derived classes that specializes the metric to be used. every child is evaluated against this method.
| node | to evaluate |
Implements mcts::MaxFunctionSelector< Context, Config >.
Definition at line 37 of file uct_selector.hpp.
1.8.15