Skip to main content
KarelPeeters's user avatar
KarelPeeters's user avatar
KarelPeeters's user avatar
KarelPeeters
  • Member for 2 years, 5 months
  • Last seen this week
4 votes
Accepted

At what point are MCTS results discarded in AlphaZero Training?

4 votes

Would AlphaZero perform better if made with transformers?

2 votes
Accepted

Reproducing AlphaZero/MuZero: Failed to beat initial model in arena

2 votes
Accepted

Why does training a NN using MCTS work even if the number of simulations isn't much larger than the number of actions?

2 votes
Accepted

Batch wise Inference to speed up Muzero's MCTS

2 votes

How does policy network learn in AlphaZero?

2 votes
Accepted

Neural Network output for the game of Checkers

1 vote

How are NNs output setup for games that allow multiple actions each turn and have very large sets of possible actions?

1 vote
Accepted

Is AlphaZero's output (action probabilities) vector suboptimal?

1 vote

MCTS: How to select children when none of them are visited?

1 vote

Is it possible for AlphaGo Zero to use recurrent networks to achieve similar performance?

1 vote
Accepted

In off-policy MC learning, why is the probability of sampling a trajectory the same as having a return?

1 vote

Can AlphaZero develop significantly different playing styles (depending on the random games from which it learrns)?

1 vote

Does AlphaGo play random moves in a real competition?

1 vote
Accepted

AlphaZero Chess: High portion of "draws" during first rounds of self-play hampers learning