Comments (4)
@sky-story Hi, thanks for the issue. I think this will resolve your issue:
$ pip install gym
$ d3rlpy install d4rl
from d3rlpy.
@sky-story Hi, thanks for the issue. I think this will resolve your issue:
$ pip install gym $ d3rlpy install d4rl
Thanks for your quick and accurate response! I wonder if these commands still work on d3rlpy==2.5.0
pip install d3rlpy
pip install git+https://github.com/Farama-Foundation/D4RL
pip install -U gym
pip uninstall pybullet
What's more,when I run the example:
import d3rlpy
# prepare dataset
dataset, env = d3rlpy.datasets.get_d4rl('hopper-medium-v0')
# prepare algorithm
cql = d3rlpy.algos.CQLConfig().create(device='cuda:0')
# train
cql.fit(
dataset,
n_steps=100000,
evaluators={"environment": d3rlpy.metrics.EnvironmentEvaluator(env)},
)
I encountered the following error message,it reminds me to update my NVIDIA driver:
RuntimeError: The NVIDIA driver on your system is too old (found version 11040).
Currently, I'm running Ubuntu 18.04.
Previously, I reinstalled the NVIDIA driver, downgrading it from version 535 to 470, as recommended by Ubuntu 18.04. After doing so, my other projects ran smoothly.
Now, I'm concerned about potential conflicts if I update the NVIDIA driver on my Ubuntu 18.04 system. Is there a risk of conflict with system drivers if I perform this update?
Additionally, I'm curious if there's a method to run d3rlpy&d4rl on the current version of the NVIDIA driver (version 11040). Any insights or suggestions would be greatly appreciated!
from d3rlpy.
I wonder if these commands still work on d3rlpy==2.5.0
pip install d3rlpy pip install git+https://github.com/Farama-Foundation/D4RL pip install -U gym pip uninstall pybullet
d3rlpy install d4rl
is essentially doing the exactly the same in background.
Additionally, I'm curious if there's a method to run d3rlpy&d4rl on the current version of the NVIDIA driver (version 11040).
d3rlpy
is nothing to do with nvidia drivers. If PyTorch runs, d3rlpy also runs. In this thread, I can't provide any further information about the nvidia-driver issue.
from d3rlpy.
I wonder if these commands still work on d3rlpy==2.5.0
pip install d3rlpy pip install git+https://github.com/Farama-Foundation/D4RL pip install -U gym pip uninstall pybullet
d3rlpy install d4rl
is essentially doing the exactly the same in background.Additionally, I'm curious if there's a method to run d3rlpy&d4rl on the current version of the NVIDIA driver (version 11040).
d3rlpy
is nothing to do with nvidia drivers. If PyTorch runs, d3rlpy also runs. In this thread, I can't provide any further information about the nvidia-driver issue.
Thanks for your kind response!I would search other method to solve it.
I will close this issue.
Thank you !
from d3rlpy.
Related Issues (20)
- [QUESTION] Logging metrics at every step of training HOT 5
- [QUESTION] difference between evaluators and OPE ? HOT 2
- FQE support .d3 file model? HOT 4
- [BUG] Issue with CUDA Device-Side Assertion Failure During Training HOT 2
- [REQUEST] Allow dynamic neural architectures to be used HOT 2
- [Question] Is it possible to only collect image observation? HOT 3
- [BUG] error when running dt on atari HOT 2
- Issue: Creating MDPDataset from CSV file in d3rlpy HOT 2
- [QUESTION] Continously increasing loss and TD error HOT 7
- [REQUEST] NotImplementedError: "save_policy method does not support tuple observation yet." HOT 4
- [QUESTION] Adding a new algorithm to d3rlpy HOT 3
- [REQUEST] save decision transformer models as TorchScript/ONNX HOT 2
- [QUESTION] multidimensional states and actions HOT 8
- [BUG] DiscreteDecisionTransformer Inference Problem, AttributeError: 'numpy.ndarray' object has no attribute 'length' HOT 4
- [Question]Just want to make sure that the "environment" metric collected by the logger of offline RL algorithms is the result used in papers HOT 2
- ValueError: too many values to unpack (expected 4) when using hopper-medium-v0 environment HOT 6
- [BUG] How to continue training from a save checkpoint HOT 2
- [QUESTION] len(observation_shape) == 1 HOT 1
- [BUG] saving and loading model with custom network gives KeyError: 'custom' HOT 3
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 d3rlpy.