When MCTS Makes You Worse
1:08:31–1:09:52 · 81s
Eric candidly describes failure modes where bad value estimates or too few simulations cause MCTS to degrade the policy instead of improving it—and how to ground training.
1:08:31–1:09:52 · 81s
Eric candidly describes failure modes where bad value estimates or too few simulations cause MCTS to degrade the policy instead of improving it—and how to ground training.
We use cookies to understand how you use our platform and to improve your experience. Click "Accept All" to consent, or "Decline non-essential" to opt out of non-essential cookies. Read our Privacy Policy.