Daydreaming Better Moves Offline
2:09:00–2:09:25 · 24s
Eric likens an off-policy relabeling approach to 'daydreaming': revisiting past states and re-planning with current MCTS to learn better decisions without fresh gameplay.
2:09:00–2:09:25 · 24s
Eric likens an off-policy relabeling approach to 'daydreaming': revisiting past states and re-planning with current MCTS to learn better decisions without fresh gameplay.
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.