causal
MCTS improvement depends on grounded value estimates
MCTS is only guaranteed to improve the policy if the value estimates at the leaves are accurate; if training data lacks late-stage resolutions (e.g., bots resign rather than play to Tromp-Taylor end), bad terminal values propagate up through backups and PUCT, making MCTS produce a worse distribution than the raw policy—so the value function must be grounded, e.g. by forcing some games to resolve fully.
causalpending
Speaker
Eric JangEvidence Quote
“If the terminal values of the leaves are not good, then this will propagate all the way up and cause your PUCT selection criteria and your backups to be off. And then you end up visiting a very different distribution than what your policy initially recommended.”
Created: 6/13/2026, 3:37:56 AM
Your notes
Loading notes...