liuanji / wu-uct Goto Github PK
View Code? Open in Web Editor NEWA novel parallel UCT algorithm with linear speedup and negligible performance loss.
License: MIT License
A novel parallel UCT algorithm with linear speedup and negligible performance loss.
License: MIT License
The code can not work when there are two or more WU-UCT players in one game ใ
Could you share the EnvWrapper file with us?
./Env/EnvWrapper.py
I wonder the max speedup of this algorithm, thx.
I'm interested your paper. However, I feel your key idea is same as the virtual loss for MCTS parallelization? what's the difference between them? Hope for your answer.
Best wishes
in tree/UCT.py 185 line, force done to False
in my opinion, the way choosing an action to expand is purely based on the prior probability or just random choice.
So why there is a while loop? I don't quite understand the "if" condintions in the loop, especially this one:
if self.children_visit_count[action] > 0 and count < 10: count += 1 continue
When I run the following commands
"python3 main.py --model WU-UCT --env-name PongNoFrameskip-v0 --MCTS-max-steps 10 --max-episode-length 3 --simulation-worker-num 2 --expansion-worker-num 2", the main process will be blocked at MCTStree.close() method. The workers cannot be terminated normally.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.