tree search
A search procedure exploring possible move sequences, used in game-playing AI; AlphaZero progressively reduced its reliance on it.
As defined in Gwern — Anonymous writer who predicted AI trajectory on $12K/year salary
Other definitions
In game-playing AI, the process of exploring possible moves and counter-moves in a branching tree structure; humans are poor at tree search compared to computers because the number of possibilities grows exponentially
AI: Grappling with a New Kind of Intelligence | World Science Festival
Where it comes up · 4
- Demis Hassabis — Scaling, superhuman AIs, AlphaZero atop LLMs, AlphaFold2 claims
- Gavin Uberti - Real-Time AI & The Future of AI Hardware - [Invest Like the Best, EP.356]2 claims
- Gwern — Anonymous writer who predicted AI trajectory on $12K/year salary1 claim
- Demis Hassabis — Scaling, superhuman AIs, AlphaZero atop LLMs, AlphaFold1 claim
Most important claims · 6 of 6Search all claims for “tree search” →
- There is a trade-off between model quality and search: AlphaZero plays beyond world-champion level using only tens of thousands of evaluated positions versus millions for brute-force systems like Deep Blue, while human grandmasters use only a few hundred—because richer, more accurate world models let you pick which nodes to expand, so improving models makes search more efficient and lets you go further.Demis Hassabis — Scaling, superhuman AIs, AlphaZero atop LLMs, AlphaFold
- Human exceptional achievement like Einstein's development of relativity is achieved through intuition built on extremely accurate world models and mental simulations rather than through Monte Carlo tree search; Einstein visualized physical systems, felt what they should be like, and had an intuitive understanding of physics that allowed him to think through possibilities with minimal explicit search.Demis Hassabis — Scaling, superhuman AIs, AlphaZero atop LLMs, AlphaFold
- People writing about AI around 2020 missed scaling because they hadn't appreciated prior scaling results (e.g. AlphaZero discovered partly via Bayesian hyperparameter optimization that revealed tree search could be reduced, and Baidu's 2017 scaling-laws paper that showed scaling laws persist), and because they shared the error of believing algorithms matter more than compute.Gwern — Anonymous writer who predicted AI trajectory on $12K/year salary
- Language models may move toward tree search, generating many candidate continuations, evaluating them, and backtracking to the best path, as chess engines do, though this has not caught on yet.Gavin Uberti - Real-Time AI & The Future of AI Hardware - [Invest Like the Best, EP.356]
- LLMs must keep improving as reliable world models—a necessary but insufficient component of AGI—and AlphaZero-like planning mechanisms should be built on top to make concrete plans, chain reasoning, and use search to explore massive possibility spaces, a capability currently missing from large models.Demis Hassabis — Scaling, superhuman AIs, AlphaZero atop LLMs, AlphaFold
- Current beam search in language models is primitive, typically using at most four beams with shallow lookahead, and it requires roughly 4x more compute, which is a large overhead, so it has not caught on.Gavin Uberti - Real-Time AI & The Future of AI Hardware - [Invest Like the Best, EP.356]