5 votes

Which AI algorithm is best for chess?

I'm not an expert in the field, but I want to draw your attention to reinforcement learning (which is also mentioned in the Wikipedia article on AlphaZero). The book "Reinforcement Learning: An ...
Peter's user avatar
  • 7,426
4 votes

Which AI algorithm is best for chess?

This is a massive question. There are two basic approaches, with the key difference being the search algorithm. The first approach, currently used by the world's strongest engine Stockfish, involves ...
Allure's user avatar
  • 275
4 votes
Accepted

What does scaling a gradient do?

Author of the paper here - I missed that this is apparently not a TensorFlow function, it's equivalent to Sonnet's scale_gradient, or the following function: ...
Mononofu's user avatar
  • 156
3 votes
Accepted

On what principle did Google's DeepMind learn to walk?

The full method is explained in the paper Emergence of Locomotion Behaviours in Rich Environments by the DeepMind team. Quoting from that paper: Using a novel scalable variant of policy gradient ...
Neil Slater's user avatar
  • 28.8k
3 votes
Accepted

Game theory in Reinforcement Learning

Where the game theory is applied when it comes to reinforcement learning? It is not used directly in this case, and AlphaStar makes no breakthroughs in game theory. The blog's wording here is not ...
Neil Slater's user avatar
  • 28.8k
3 votes

How Exactly Does In-Context Few-Shot Learning Actually Work in Theory (Under the Hood), Despite only Having a "Few" Support Examples to "Train On"?

I highly recommend you read Microsoft's recent paper about In Context Learning. Although the focus is on LLM I think it can be generalised to other models. The idea is to consider models as mesa|meta-...
Xmaster6y's user avatar
2 votes
Accepted

Question on embedding similarity / nearest neighbor methods [SCANN Paper]

It is a shame they don't give a better reference for their O(log(N)) isn't it. You asked for papers, and the obvious starting point is the one the SCaNN library is ...
Darren Cook's user avatar
2 votes

Which AI algorithm is best for chess?

AlphaZero algorithm was implemented in Leela Chess Zero and was actually one of the leaders at least before Stockfish implemented its own NN assistant algorithm. Here: https://en.wikipedia.org/wiki/...
Валерий Заподовников's user avatar
1 vote

Which AI algorithm is best for chess?

I would recommend a classical AI approach. I suggest you implement a Minimax with depth limiting or A* with depth limiting. In these scenarios, you basically rebuild the game tree and try all moves ...
Meowxiik's user avatar
1 vote

How to train a policy and a value network, implementing alphazero at chess

im pretty sure that in training games they make it so the network always sees the position from their position so that its not learning good positions for some sides but instead looking at the ...
Stefan Österberg's user avatar
1 vote
Accepted

Which Policy Gradient Method was used by Google's Deep Mind to teach AI to walk

They used Distributional Proximal Policy Optimization (DPPO). In the article that video is associated to, they provide a brief overview of it: In order to learn effectively in these rich and ...
noe's user avatar
  • 25.6k
1 vote

Is the "training loop" used in AlphaGo Zero the same as an "epoch"?

I think they did the second option. If their network is fitted to a mini batch of 2,048 states for 1,000 epochs, it will be overfitted to the sampled 2,048 states. The trained network would be less ...
Dish's user avatar
  • 111
1 vote

What does scaling a gradient do?

Given that its pseude code? (since its not in TF 2.0) I would go with gradient clipping or batch normalisation ('scaling of activation functions')
Noah Weber's user avatar
  • 5,669
1 vote
Accepted

AlphaGo Zero loss function

The best way to understand that part is by looking at figure 1 in the AlphaGo Zero paper. The neural network (NN) minimizes the differences between its own policy $p_t$ and the MCTS policy $\pi_t$. ...
Jonathan's user avatar
  • 5,400

Only top scored, non community-wiki answers of a minimum length are eligible