Epstein Secrets

is learned faster (9s67 instead of 21s47 for co:Q. Conversely the results for lamb show that when action sequence building-block is enabled, if the Occam's razor is too weak it can dramatically slow down the search. That is because in this circumstance the search is misled by longer candidates that fi

resent is carried out, either by - PLN inference within OpenCog, drawing the conclusion that a block is present from the exported predicates, using ImplicationLinks comprising a working definition of a "block" - A predicate comprising the definition of "block", previously imported into DeSTIN from OpenCog and

re learning" - it's not actually a procedure learning process, but rather a process that utilizes the fruits of procedure learning. The well-known "Occam's razor" heuristic says that all else being equal, simpler is better. This notion is embodied mathematically in the Solomonoff-Levin "universal prio

ms an action and achieves a goal. There is code to create implications based on these conjunctions. After finding many conjunctions, it can produce ImplicationLinks based on some of them. Here is an example where the Al-controlled virtual robot discovers how to get energy. (ImplicationLink (AndLink (Evaluatio

have come to the following conclusions: • for relatively straightforward procedure learning problems, hilldimbing with random restart and a strong Occam bias is an effective method • for more difficult problems that elude hinclimbing, probabilistic evolutionary program learn- Mg is an effective metho

ergoals like gaining knowledge are not funded as much with STI currency just now, as they are not immediately relevant. Action selection, based on ImplicationLinks derived via PLN (between various possible activ- ities and the subgoal S) causes it to start experimentally building some blocks structures. Past ex