Search That Teaches Itself
1:00:34–1:02:01 · 87s
Eric shows how MCTS sharpens the policy each move and then trains the network to predict the searched distribution next time—distilling expensive search into a fast forward pass.
1:00:34–1:02:01 · 87s
Eric shows how MCTS sharpens the policy each move and then trains the network to predict the searched distribution next time—distilling expensive search into a fast forward pass.
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.