Comments (3)
Hello, thank you for your feedback. Currently, our repository includes an open-source implementation similar to SampledMuZero, which is the only example available since the original authors did not release their source code. Consequently, our implementation may differ from the original in aspects such as network architecture, loss functions, hyperparameters, and training processes. These differences could be one of the reasons for suboptimal performance and instability in training our SampledEfficientZero in continuous action spaces, such as Mujoco. A robust and stable open-source implementation of SampledMuZero would be highly valuable to the community and warrants further investigation. We plan to delve deeper into this matter and will provide updates here. Thank you once again for your valuable input and patience.
from lightzero.
Thank you for detail response ~
I will try to optimize for this.
If I have any conclusion, I will share with you.
from lightzero.
Hello, we have successfully implemented SampledMuZero and SampledUniZero in this pull request, and have also optimized the previous SampledEfficientZero. Currently, all three algorithms can reliably achieve near-optimal returns within 200k environment steps in the LunarLander and BipedalWalker environments. We encourage you to test them locally.
In the DMC (DeepMind Control Suite), we have also managed to achieve near-optimal returns within approximately 500k environment steps in the Cartpole-Swingup and Walker-Walk environments (state-input). Performance in other DMC environments is still under active tuning. We will keep you updated with any relevant progress as we continue our work. Thank you for your patience.
from lightzero.
Related Issues (20)
- Great!!! HOT 1
- Running a trained agent HOT 2
- Hyperparameter of Muzero and reproducibility of the results HOT 2
- Render and plot results: is there a code snippet? HOT 1
- Bad performance on long run on MsPacman and SpaceInvaders HOT 10
- Instillation Failure on Mac (Spyder) HOT 3
- Could you provide detail code example to customize the env and algo that can run successfully in a entire file? HOT 7
- Clipping reward in Atari while using invertible transform for reward and value target HOT 2
- Issues related to the operating environment HOT 4
- Clarification on the relationship between num_unroll_steps and infer_context_length in UniZero HOT 9
- Need Help with Storing and Using Best Checkpoint with ONNX Model in LightZero HOT 1
- Unexpected performance drop after resuming UniZero training HOT 3
- Implementation of Self-Play Training for Real-Time Environments HOT 2
- Flexible Input Image Size Support for UniZero: Implementation Timeline and Contribution Opportunity HOT 5
- Inquiry about Commented Out Loss Calculations in UniZero Implementation HOT 2
- Unexpected Negative Values for Perceptual Loss in UniZero Implementation HOT 3
- When will Chess be supported for AlphaZero/MuZero? HOT 7
- Discussion: Requesting assistance and guidance with implementation of RL algorithms and models in the context of Tetris HOT 3
- Configs are unrunnable due to ImportError of smz_tree HOT 2
- How can i use TeaforN loss HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lightzero.