2 * Manual page - full usage documentation
3 * GTP interface documentation
6 * Further optimize board implementation, oprofile fun
7 * Clean up GTP interface, allow custom GTP commands for modules
8 * Implement parameter setup over GTP
9 * gogui-friendly GTP interface
14 * MM local-based patterns
15 * Balanced local-based patterns?
18 * Reverse status learning
19 Run on game corpus. Start at final position, watch development
20 of status of all stones. The moment the final status and expected
21 status changes, analyze, especially if move choice differs. Use
22 learnt status-fixing moves in simulations somehow.
25 * Split playout aspects to custom-stackable pieces
26 * Possibly replay top-rated unplayed moves from the tree
30 * Fix RAVE for good (still noticeably weaker than fuego?)
31 * Separate constants for prior and amaf elements?