Comments (3)
There's currently no way to do this. You'd have to implement sticky actions yourself on top of the environment. Out of curiosity why would you want to do this?
from atari-py.
While this may not be a native feature, is there any way I could modify the gym code directly to do something like this that you are aware of?
I am trying to train a model to extract actions from sequences of frames. The offline RL datasets I have been using were generated with repeat_action_probability = 0.25
, meaning that 25% of the ground truth action labels in the datasets are garbage. So I wanted to regenerate the exact same data, but with knowledge of the actually executed action. Having the exact same data (frame-by-frame, not just the same protocol) but with the actually executed actions will allow me to use these standard offline RL datasets to benchmark my model.
from atari-py.
So the short answer is yes, you can easily use environment wrappers, check out some of the built-in wrappers here: https://github.com/openai/gym/tree/master/gym/wrappers. You could also just as easily implement this on top of Gym without wrappers, just do the sampling yourself when interacting with the environment.
I still don't fully understand your use case. If you have an offline RL dataset the actions in the dataset are presumably the agent's chosen actions, not the actions the environment will execute, I don't see how 25% of your action labels are garbage? If sticky actions were enabled when you generated the dataset then perhaps 25% of your transitions wouldn't correspond to the ground truth emulation, i.e., S_{t+1} is a stochastic function S_t, A_t due to sticky actions, the only source of stochasticity in the ALE. Do you really want to remove this stochasticity? Generally, it should be assumed that this is part of the environment dynamics.
If you don't want any form of stochasticity you could just generate the dataset with sticky actions disabled?
from atari-py.
Related Issues (20)
- Building requires zlib1g-dev, not just zlib1g HOT 1
- Update atari-py from upstream ALE HOT 1
- OSError: [WinError 126] The specified module could not be found HOT 2
- OSError: [WinError 126] Cannot find the specified module HOT 1
- package license in pypi distribution HOT 1
- Compatilbility with Python 3.8? HOT 2
- Cannot find the game surround that is part of the Atari57 benchmark HOT 3
- why file dowloaded from Atari 2600 VCS ROM Collection is so big? my 450GB free space is not enoough HOT 2
- Breakout doesn't end after losing the game HOT 2
- Publish wheels for 3.8 HOT 1
- Exception: ROM is missing for ms_pacman, see https://github.com/openai/atari-py#roms for instructions HOT 4
- Rom is missing, Fix that please X-X HOT 3
- Problem in Google colab with "Breakout" game in OpenAI Gym (ROM missing) HOT 6
- error installing the ROM HOT 1
- NO error, but can still not run Pong-0 HOT 3
- ROM MD5s differ
- Unable to load ROMs with ale.loadROM() HOT 2
- Unable to import ROMS HOT 1
- Tetris.bin ROM file is broken or corrupted
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 atari-py.