Evgeniy Simonenko

Add support for truffleruby (22.1.0). Cause this feature is not supported by truffleruby (22.1.0) yet: https://github.com/oracle/truffleruby/blob/master/doc/user/compatibility.md#standard-libraries Without commit PR got error: ``` core/kernel.rb:236:in `gem_original_require': cannot load such file -- pty...

# System Plugin Version: 17.0.0 Application: IntelliJ IDEA Ultimate Edition (2023.3.3) Operating System: Windows 11 (10.0) # Event ## Exception ### Stacktrace com.intellij.diagnostic.PluginException: Cannot check provider org.elixir_lang.beam.file_editor.Provider [Plugin: org.elixir_lang] ```...

Support rollback to savepoint after failure

5

### Questions I have encountered some strange transaction behaviour. If I execute a query after the transaction starts, create a checkpoint, then this query terminates with an exception (in my...

Unexpected Negative Values for Perceptual Loss in UniZero Implementation

3

I am currently conducting experiments with the UniZero neural network using your library. During my research, I've observed that when incorporating perceptual loss in the UniZero model, the loss values...

Flexible Input Image Size Support for UniZero: Implementation Timeline and Contribution Opportunity

5

I'm currently conducting experiments with the UniZero neural network using your library. I'm interested in the timeline for implementing flexible input image size support in UniZero, given the presence of...

Inquiry about Commented Out Loss Calculations in UniZero Implementation

2

While examining the source code for UniZero calculations in the master branch, I noticed that the latent_recon_loss and perceptual_loss computations are currently commented out. I'm curious whether this was an...

Implementation of Self-Play Training for Real-Time Environments

2

I'm currently conducting experiments with the UniZero neural network using your library. I'm particularly interested in understanding the feasibility of implementing self-play training for UniZero in real-time environments, such as...

Unexpected performance drop after resuming UniZero training

1

I've been experimenting with UniZero training using the default configuration (atari_unizero_config.py). The initial training process progressed well, aligning with the expectations set in the paper. However, I've encountered an issue...