Comments (3)
agarwl
commented on May 17, 2024
Hmm .. I'm also not sure what could be causing the issue but we have used Asterix/1 for some of our recent ICLR/NeurIPS papers and it does seem to replicate internally -- That said, I do know CQL authors had difficulty replicating the results on Asterix, so there might be some chance the dataset might be corrupted. If this is time sensitive, feel free to ignore this specific run. I'll also compare the checksums of the public data and the internal data.
One thing that you can check is whether the clipped rewards match in the dataset with the TFDS version of the dataset (see this colab for an example of how to load the dataset).
from batch_rl.
dssrgu
commented on May 17, 2024
Thank you for the response!
I'll ignore this dataset for right now.
Just to let you know, below is the training curve for Asterix/1 and Asterix/2:
Thank you!
from batch_rl.
agarwl
commented on May 17, 2024
This is probably too late but I re-uploaded the entire dataset for run 1 from the copy we have internally. Hopefully, this would fix the issue.
from batch_rl.
Related Issues (20)
- Can a customized env be added to the current framework? HOT 1
- The flag 'base_dir' is defined twice HOT 3
- Python version? HOT 2
- Reading atari files directly. HOT 3
- How to evaluate agents? HOT 2
- Why use a small batch size? HOT 2
- No module named 'dopamine.google' HOT 2
- a minor modification for download command HOT 1
- Transform matrix create only once? HOT 2
- WARNING:absl:Unable to find episode_end_indices. This is expected for old checkpoints. HOT 1
- JAX code HOT 11
- How to get expert data ? HOT 5
- About DQN replay dataset HOT 2
- Difference b/w checkpoint 49 and checkpoint 50 HOT 5
- A copy of the dataset? HOT 1
- only action checkpoint in https://console.cloud.google.com/storage/browser/atari-replay-datasets HOT 1
- configurable() got an unexpected keyword argument 'blacklist' HOT 2
- About terminal in Atari dataset HOT 1
- Windows: basic test failed 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 batch_rl.