-
# Tabula Rasa Learning Approach Proposal
## Summary
I propose implementing a "Tabula Rasa" (clean slate) learning approach for our project, where the system starts with minimal prior knowledge and…
-
https://github.com/mokemokechicken/reversi-alpha-zero/blob/5ee2f330663b34513f0c894eb658f03a1201f400/src/reversi_zero/agent/player.py#L115-L121
I first think this code is searching in the simulation…
-
SAI Team:
First, Thank you for your research to provide the free strong Go Engine and give us a different idea to implement it.
Since the 2019 SAI's paper, SAI: a Sensible Artificial Intellige…
-
As of now, Lc0's search is still using AlphaZero's original PUCT, with a few modifications in WDL+draw score, some certainty propagation, and the general batching strategy. This certainly works decent…
-
-
As training networks from scratch is "incredibly wasteful", do people perhaps share their AlphaZero.jl trained networks anywhere? I've read the docs and haven't seen that mentioned!
Also I have a m…
-
I can't run any code with parl, always getting that error.
This is how I start on my local machine, Windows 10:
```
xparl start --port 8010
# The Parl cluster is started at localhost:8010.
# …
-
its winrate vs lz236 is only 52% after 340 games.
193 : 182 (51.47%) 375 / 400
-
Did you consider or even already experiment with having the network predict the remaining number of moves in a game? Game length is admittedly kind of a dubious concept in the game of go (depending on…
-
Investigation in to possible reasons for the cascading failure of value head quality after v0.8 was released, suggested PUCT and fpu-reduction changes as likely causes.
If we believe that these value…
Tilps updated
6 years ago