jonathan-laurent/AlphaZero.jl
A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.
JuliaMIT
Pinned issues
Issues
- 0
Which hardware is recommended for non-trivial games?
#214 opened by StepHaze - 0
Can't get connect four example to work
#213 opened by zoetiskool - 1
Generic POMDP Support
#212 opened by nateybear - 0
supervised learning
#210 opened by StepHaze - 6
Non-trivial games
#209 opened by StepHaze - 6
got Out of GPU memory when learning
#202 opened by A-Cepheus - 2
Success stories
#185 opened by StepHaze - 3
Success report and request for help
#201 opened by bwanab - 3
Game proposition: BonbonRectangle
#149 opened by smart-fr - 1
Not invoking alternate implementation of select_move
#199 opened by bwanab - 3
How to restart a training session that has completed
#198 opened by bwanab - 1
- 0
How important is loss during learning
#197 opened by StepHaze - 0
Julia 1.9?
#196 opened by smart-fr - 0
How many iterations are required?
#195 opened by StepHaze - 2
When should I stop learning?
#194 opened by StepHaze - 2
Any way to start when playing against AlphaZero?
#192 opened by pepa65 - 2
AZ much worse than generic solution for simple game
#193 opened by 70Gage70 - 0
LoadError: UndefVarError: #flatten not defined
#191 opened by smart-fr - 9
How to prevent GPU OOM?
#186 opened by pepa65 - 1
I can't install it to run training
#190 opened by StepHaze - 4
[Feedback Requested] Wishlist for the next major release of AlphaZero.jl
#181 opened by jonathan-laurent - 3
Issue with ternary outcome statistics
#177 opened by gwario - 2
What next after training an agent?
#187 opened by pepa65 - 1
Maximum number of iterations
#184 opened by StepHaze - 4
Training Stuck at 'Network Only against MinMax (depth 6)' after Modifying TicTacToe Board Size to 4x4
#180 opened by solidcub - 9
ERROR: Out of GPU memory
#174 opened by smart-fr - 3
Is it worth to continue training after the memory buffer was filled with samples?
#176 opened by smart-fr - 13
Hardware sizing with regards to problem complexity
#165 opened by smart-fr - 2
Error using KNET
#172 opened by smart-fr - 5
Trouble Installing from GitHub
#173 opened by Bobingstern - 1
How to use AlphaZero in kaggle kernel?
#161 opened by Snimm - 1
Internal error: encountered unexpected error in runtime: ReadOnlyMemoryError() Exception: UNKNOWN at 0x7ffae516cd29 --
#175 opened by Snimm - 2
Inference time "PTX compile error: Entry function uses too much parameter space"
#171 opened by smart-fr - 3
Freeze network parameters
#166 opened by gwario - 2
- 4
- 2
Can I save time on benchmarks?
#167 opened by smart-fr - 1
Tutorial to setting up solving your own game
#157 opened by smart-fr - 4
Stack overflow with lots of RAM still available
#164 opened by smart-fr - 3
Help: dummy_run stuck
#162 opened by smart-fr - 2
- 2
Support for multiplayer games?
#159 opened by kendonB - 6
Having trouble using AlphaZero.jl in Google Colab
#155 opened by Snimm - 2
Trouble installing AlphaZero.jl
#156 opened by smart-fr - 1
NVIDIA GeForce GTX 1650 isn't good?
#151 opened by StepHaze - 1
Does it work with Tesla?
#154 opened by StepHaze - 3
What's the best OS for AlphaZero.jl ?
#153 opened by StepHaze - 3
TicTacToe MCTS example script freezes
#148 opened by viktmar - 1
num_filters=128
#150 opened by DmitriMedved