muzero-general
studio
muzero-general | studio | |
---|---|---|
14 | 35 | |
2,379 | 1,692 | |
- | - | |
0.0 | 9.8 | |
4 months ago | about 2 months ago | |
Python | TypeScript | |
MIT License | Mozilla Public License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
muzero-general
-
Open source rules engine for Magic: The Gathering
I went looking for MuZero implementations in order to see how, exactly, they interact with the game space. Based on this one, which had the most stars in the muzero topic, it appears that it needs to be able to discern legal next steps from the current game state https://github.com/werner-duvaud/muzero-general/blob/master/...
So, I guess for the cards Forge has implemented one could MuZero it, but I believe it's a bit chicken and egg with a "free text" game like M:TG -- in order to train one would need to know legal steps for any random game state, but in order to have legal steps one would need to be able to read and interpret English rules and card text
- I placed Stockfish (white) against ChatGPT (black). Here's how the game went.
- Ask HN: What interesting problems are you working on? ( 2022 Edition)
-
How to "fit" the output of the Critic to the dimension of the reward?
You may want to use the trick described in https://arxiv.org/pdf/1805.11593.pdf as a Transformed Bellman Operator. Its efficiency is proved in MuZero original paper https://arxiv.org/pdf/1911.08265.pdf Appendix F. The implementation of that method you can find here: https://github.com/werner-duvaud/muzero-general Usage: muzero/models.py:649 (def support_to_scalar)
-
MuZero unable to solve non-slippery FrozenLake environment?
I have used this implementation from MuZero: https://github.com/werner-duvaud/muzero-general
-
RL for chess
+1 to taking a look at OpenSpiel. It has AlphaZero in C++ and Python, and there is even a PR open that allows running UCI (e.g. Stockfish) bot. You can also load chess via the OpenSpiel wrapper in muzero-general: https://github.com/werner-duvaud/muzero-general
-
The future of MuZero, and where to go for news
When I looked up some community implementations, like that of Werner Duvaud on GitHub and Discord, hoping to make my own contributions to this effect, I soon found that I was hopelessly out of my depth as an amateur programmer, even with the help of some other sources like this walkthrough series. However, from what I could tell, most of the people working on this sort of thing seemed to be tackling relatively simple games. At first I thought this might be largely due to limitations in hobby time or computing power available to these users, but then I also noticed that, unless I have misunderstood something, it seems like the games are required to be rebuilt entirely in the engine of (this implementation of) MuZero, which would also obviously be a limit on the complexity of games chosen.
- Is MuZero currently the best RL algo that we have now?
-
"muzero-general", PyTorch/Ray code for Gym/Atari/board-games (reasonable results + checkpoints for small tasks)
Windows support (Experimental / Workaround: Use the notebook in Google Colab)
-
Muzero code implementation
There are several if you google "muzero github", e.g. https://github.com/werner-duvaud/muzero-general
studio
-
ROS 2 Iron Irwini Release
> Especially a tool like RViz is always missing. And in many many robotics video I see (of a moderately complex robot), there's ROS's RViz on some screen.
I would love the future robotics development stack to be more modular, so that (for example) future middleware solutions don't need to also bundle their own visualization software. This was direct inspiration for creating Foxglove Studio[0] for visualization and MCAP[1] for logging - both work great with ROS, or equally well without it.
[0] https://github.com/foxglove/studio
[1] https://github.com/foxglove/mcap
-
Generic eCAL / Foxglove Communication Bridge
That's the true strength of combining existing open source solutions. Thanks for the great support of Foxglove Inc. over the past few years.
-
Ask HN: Who is hiring? (March 2023)
Foxglove | Remote (US time zones) | Full Time or Contract | https://foxglove.dev/
Foxglove is the leading observability platform for robotics developers. We help robotics and AV companies log, ingest, organize, and visualize multimodal data. Join our small, highly experienced, and fast moving team. Prior experience working in robotics or AV is a bonus but not necessary.
* Senior Frontend Engineer (TypeScript, React, bonus if you have WebGL experience)
* Senior Full Stack Engineer (TypeScript, Go)
* Senior SRE/Infrastructure/DevOps Engineer (GCP, AWS, Azure, Terraform, K8s)
https://foxglove.dev/careers
Email in profile if you have questions.
-
Sniper robot treats 500k plants per hour with 95% less chemicals
It's a common misconception that you need a ML or robotics PhD to work in the field. There are plenty of frontend & backend web engineering, data engineering, and infrastructure/devops roles available at robotics companies - you don't need to be a domain expert.
For example, at Foxglove[0] we are building open source web-based visualization and data management for robotics (shameless plug: currently hiring).
[0] https://foxglove.dev/
-
Understanding a Small ROS bag file
You can use the rosbag commandline-tool to figure out all of this: http://wiki.ros.org/rosbag/Commandline rosbag info for example can give you some of the type/number of messages information. For more complex stuff, you could use https://foxglove.dev/ to visualize and inspect rosbags
-
Ask HN: What interesting problems are you working on? ( 2022 Edition)
Web-based data visualization for robotics and self-driving. Robotics is such an interesting industry, and we're only scratching the surface of what new tools are needed.
Try it live here (hit "view sample data"): https://studio.foxglove.dev/
And it's open source! https://github.com/foxglove/studio
Shameless plug - we're hiring: https://foxglove.dev/careers
-
Recording your JSON data to MCAP, a file format that support multiple serialization formats
When our team at Foxglove announced MCAP, we wanted to empower teams to spend less time building commodity tools and more time tackling their hardest robotics challenges.
- Brainstorming ideas for a cloud/web based control system for construction robotics
-
Ask HN: Who is hiring? (June 2022)
Foxglove | Remote (Americas/Oceania) | Full Time or Contract | https://foxglove.dev/
Dev tools for robotics and autonomous vehicles.
Robotics will have a massive positive impact on the world economy and global human productivity over the coming decade. At Foxglove, we're building powerful web-based open source & commercial tools to accelerate this trend.
We're a small, highly experienced, and fast moving team. We're looking to hire several more people (most roles don't require previous robotics experience, unless specified below):
- Senior Frontend Engineer (react, typescript, some webgl+wasm)
- Senior Full Stack Engineer (typescript, some golang)
- First Product Manager (robotics/AV experience required)
- First Account Executive (infrastructure SaaS experience required)
https://foxglove.dev/
https://foxglove.dev/careers
-
Ask HN: Can you share websites that are pushing the utility of browsers forward?
React + Typescript. Forgot to mention itβs open source so you can see for yourself:
https://github.com/foxglove/studio
What are some alternatives?
deep-RL-trading - playing idealized trading games with deep reinforcement learning
webviz - web-based visualization libraries
Super-mario-bros-PPO-pytorch - Proximal Policy Optimization (PPO) algorithm for Super Mario Bros
Grafana - The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.
alpha-zero-general - A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more
TimescaleDB - An open-source time-series SQL database optimized for fast ingest and complex queries. Packaged as a PostgreSQL extension.
open_spiel - OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
PostHog - π¦ PostHog provides open-source product analytics, session recording, feature flagging and A/B testing that you can self-host.
stable-baselines3-contrib - Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
cli - Official Command Line Interface for the IPinfo API (IP geolocation and other types of IP data)
pytorch-ddpg - Deep deterministic policy gradient (DDPG) in PyTorch π
jamstack.org - The official Jamstack site