Timeline for AlphaZero Chess: High portion of "draws" during first rounds of self-play hampers learning
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 28 at 8:31 | vote | accept | Oliver Ewald | ||
| Jan 26 at 8:09 | comment | added | Oliver Ewald | Thanks a lot for clarification! I will test with modified termination rules. | |
| Jan 25 at 22:23 | comment | added | KarelPeeters | @OliverEwald I only terminate games based on 3-fold repetition, the 50 move rule and insufficient material (only king vs king). For this run the average game length started at 100, peaked at 300 and then dropped back down to 110. Cutting of games at 100 moves indeed causes lots of draws, so that's probably your main issue! | |
| Jan 24 at 19:57 | comment | added | Oliver Ewald | 1. I will do new random checks (without MCTS) to see if my win ratios will go up towards your 14% 2. I just checked that my MCTS clearly detects "mate in one" 3. What I find surprising is that your MCTS on a fully uninitialized NN only finds 17% draws. That's far off from my 97% 4. Currently I define a game as "drawn" if there is no mate after 100 moves. What rules do you apply to avoid endless games? 5. I will answer back here once I have 1. completed with (possibly) adjusted rules how to define draws. | |
| Jan 24 at 19:41 | comment | added | Oliver Ewald | Thanks a lot for your quick and comprehensive answer! | |
| Jan 23 at 21:17 | history | answered | KarelPeeters | CC BY-SA 4.0 |