Comments (4)
@junyeop Hi, thanks for the issue. Currently, this is a little tricky to support due to weirdness of torch.script
. But, I'll look into this for the next release.
from d3rlpy.
@takuseno Hi, thank you for your reply. I'll be looking forward to the next release.
from d3rlpy.
@junyeop Hi, I've supported this functionality at this latest commit: 9e7d59a . If you install d3rlpy from the source, you can use this feature. When you use the saved policy, you need to do as follows:
TorchScript
policy = torch.jit.load("tuple_policy.pt")
# infer the action
tuple_observation = [torch.rand(1, 3), torch.rand(1, 5)]
action = policy(tuple_observation[0], tuple_observation[1])
ONNX
ort_session = ort.InferenceSession('tuple_policy.onnx', providers=["CPUExecutionProvider"])
# infer the action
tuple_observation = [np.random.rand(1, 3).astype(np.float32), np.random.rand(1, 5).astype(np.float32)]
action = ort_session.run(None, {'input_0': tuple_observation[0], 'input_1': tuple_observation[1]})
from d3rlpy.
Let me close this issue since the request has been supported. This feature will be included in the next release.
from d3rlpy.
Related Issues (20)
- Differences in RTG computation between inference and training time HOT 2
- [QUESTION] Custom evaluators not working. HOT 4
- [QUESTION] How to implement a new algorithm? Any guidelines? HOT 1
- [QUESTION] Importing Stable Baselines3 (SB3) Models into d3rlpy HOT 4
- [QUESTION] Issue with Evaluating Decision Transformer Using Evaluators in d3rlpy HOT 1
- [BUG] FQE Loading .d3 errors HOT 1
- a question about d3rlpy 1.1.1 install bug HOT 2
- Issue when using d3rlpy.load_learnable() to load trained model HOT 3
- [REQUEST] Annealing schedule of hyperparameters HOT 1
- create own environment HOT 4
- [Compilation error] Cython.Compiler.Errors.CompileError when running hopper example HOT 1
- Add EfficientZeroV2?
- encoder HOT 3
- Test the trained policy
- [REQUEST] Softmax activation function for encoders HOT 1
- [BUG] MDPDataset action space identifier failed HOT 1
- [QUESTION] Issue with Large Dataset in Distributed Training HOT 5
- Set the random seed of gym environments for fit_online and evaluation HOT 3
- Reduction in TD loss for ensemble Q networks
- Alteration to default summation used to define TD loss of ensemble Q functions
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.