Comments (11)
@pstansell Hi, sorry for being late. Now eval_interval
argument is available.
0d91df6
from d3rlpy.
@takuseno, thanks for adding eval_interval
, but I can only see it available in fit_batch_online()
, not in fit_online()
, which is where I wanted to use it.
from d3rlpy.
Ah, sorry. I've added save_interval
to both methods.
from d3rlpy.
After further experimentation, I think v0.51 already had the argument I wanted to control the rate at which model files were written, that is,
save_interval – interval to save parameters.
I hadn't realised what it did. Sometimes I struggle to understand exactly what the fuction arguments do based on their names and descriptions. But, anyway, the problem is solved now so I will close the issue. You make changes so quickly, it's hard for me to keep up :-). Thanks very much!
from d3rlpy.
@takuseno, it seems that fit_online()
does not allow argument eval_interval
.
from d3rlpy.
No, fit_online
does not have that option. But you can control save frequency with save_interval
.
from d3rlpy.
But doesn't that mean that I have to save models at the same rate as metrics? Put another way, the number of lines in metric files, for example time_step.csv
, will be the same as the number of output files named model_*.pt
. My initial desire was to be able to save model files at a lower rate than metrics. Given the current input arguments, I'm not sure if I can do that.
from d3rlpy.
The saved model file name and the epoch number in metrics will match. So, if you give save_interval=2
, the files and metrics will be like below.
metrics
0,xxx,yyy
1,xxx,yyy
2,xxx,yyy
3,xxx,yyy
4,xxx,yyy
.
.
model files
model_0.pt
model_2.pt
model_4.pt
.
.
from d3rlpy.
Oh, wait. I found my bad. I'll fix this.
d3rlpy/d3rlpy/online/iterators.py
Line 258 in 0d91df6
from d3rlpy.
@pstansell I've fixed this in the last commit.
b6c9b69
from d3rlpy.
I tested it and confirm that it's fixed now. Thanks very much.
from d3rlpy.
Related Issues (20)
- [REQUEST] More control over logging options HOT 1
- [Question] Reproducing FQE HOT 6
- [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
- d3rlpy install d4rl HOT 4
- 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
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.