Arthur Juliani
@awjuliani.bsky.social
You can try it out in your browser here: awjuliani.github.io/web-rl-playg...
Or run it locally on your own machine and play with the code using the GitHub repo here: github.com/awjuliani/we...
I hope people find it useful/fun. Very open to feature requests or feedback!
Or run it locally on your own machine and play with the code using the GitHub repo here: github.com/awjuliani/we...
I hope people find it useful/fun. Very open to feature requests or feedback!
The Beginner's RL Playground
awjuliani.github.io
April 28, 2025 at 2:20 PM
You can try it out in your browser here: awjuliani.github.io/web-rl-playg...
Or run it locally on your own machine and play with the code using the GitHub repo here: github.com/awjuliani/we...
I hope people find it useful/fun. Very open to feature requests or feedback!
Or run it locally on your own machine and play with the code using the GitHub repo here: github.com/awjuliani/we...
I hope people find it useful/fun. Very open to feature requests or feedback!
In addition to the basic algorithms like Q-Learning, I also included slightly more advanced ones like the Successor Representation. The tool lets you see the successor maps for each state as the agent moves through the environment, which I think makes them much more intuitive!
April 28, 2025 at 2:20 PM
In addition to the basic algorithms like Q-Learning, I also included slightly more advanced ones like the Successor Representation. The tool lets you see the successor maps for each state as the agent moves through the environment, which I think makes them much more intuitive!
Code for the project is available here: github.com/awjuliani/dr...
GitHub - awjuliani/dream-jrpg: An experiment in using LLMs to procedurally generate simple Japanese-style RPGs.
An experiment in using LLMs to procedurally generate simple Japanese-style RPGs. - awjuliani/dream-jrpg
github.com
January 22, 2025 at 6:54 PM
Code for the project is available here: github.com/awjuliani/dr...
It was a fun project to work on, and I learned a lot about the strengths and limitations of current LLMs for this kind of storytelling. I can't claim that any of the games that this generates are actually *good*, but I think they are at least amusing in their idiosyncrasies.
January 22, 2025 at 6:54 PM
It was a fun project to work on, and I learned a lot about the strengths and limitations of current LLMs for this kind of storytelling. I can't claim that any of the games that this generates are actually *good*, but I think they are at least amusing in their idiosyncrasies.