Skip to content
All tags

#alphazero

2 posts
ai deep-dive Reading CMU 07-280

CMU 07-280 Lecture 24: How Monte Carlo Tree Search Connects to AlphaZero

Spring 2026 Lecture 24 is MCTS, not Fall 2026 LLM post-training. It allocates simulations through selection, expansion, rollout, backup, and UCB, then connects policy/value heads and self-play to AlphaZero.

#cmu#ai-course#monte-carlo-tree-search#alphazero#reinforcement-learning
ai deep-dive Reading CMU 07-280

CMU 07-280 Stage Review III: From MDPs and Q-learning to AlphaZero

Stage III connects value, policy, bootstrapping, function approximation, and MCTS into AlphaZero: a network supplies priors and estimates, search improves decisions, and self-play creates the next training set.

#cmu#ai-course#reinforcement-learning#mcts#alphazero