BSD Testbench

Test Systems Games Score Elo SPRT Status
todo: new large vs old large (copy) new vs base 102 0.520 13.6 Done
todo: new large vs old large new vs base 42 0.488 -8.3 Cancelled
test new value+policy together (fix) (copy) new vs new-policy 18 0.389 -78.5 Cancelled
test new value+policy together (fix) new-policy vs new-policy 0 0.000 0.0 Cancelled
test new value+policy together (copy) (copy) new-policy vs new-policy 2 0.500 -0.0 Cancelled
test new value+policy together (copy) new-policy vs old 0 0.000 0.0 Paused
test new value+policy together new-policy vs old 0 0.000 0.0 Cancelled
test new policy net (copy) (with book) (copy) new-policy vs old-policy 64 0.516 10.9 Paused
test new policy net (copy) (with book) (copy) new-policy vs old-policy 0 0.000 0.0 Cancelled
test new policy net (copy) (with book) new-policy vs old-policy 66 0.515 10.5 Paused
test new policy net (copy) new-policy vs old-policy 4 0.500 -0.0 Cancelled
test new policy net new-policy vs old-policy 46 0.391 -76.8 Paused