Comments (6)
Split by exp_name
or unique_id
.
from rlkit.
Thanks for catching the bug. The example script is now fixed (see 9803d09) so that it runs.
I'll test it a bit more on my end and see if I get similar results. I also emailed the HER authors to see if they have suggestions, and will update accordingly.
from rlkit.
In my experience the reacher will usually end up working with the default settings in that script, but it may take many more epochs than the screenshot in the HER Readme. However, the other tasks I have not gotten to work
from rlkit.
I just ran 5 seeds of the example script and got the following results:
So while the variance across seeds might be high (one seed fails completely, the others 4 succeed), I'm going to close this issue since it seems to be working.
from rlkit.
@vitchyr Hey vitchyr how do you get the plots to separate as individual lines per seed versus accumulating as variance shading over one line?
from rlkit.
The comments at the top of the HER scripts are confusing ("This should results in an average return of ~3000 by the end of training."). I think they aren't meant for the environments in the script?
from rlkit.
Related Issues (20)
- rlkit/torch/networks/stochastic not installed HOT 1
- unable to create the conda environment with linux-cpu-env.yml HOT 2
- Issue SMAC algorithm HOT 4
- multi-GPU optimised implementations for running algorithms HOT 1
- Doubt on Q-function loss in AWAC HOT 1
- Question about VAEPolicy in rlkit.torch.sac.policies HOT 2
- CustomMDPPathCollector is not found HOT 2
- Doubt on advantage calculation to update the policy on AWAC.
- Position Control with mujoco-py
- Cannot reproduce the results of IQL on antmaze HOT 1
- High Memory & Disk Requirement for SMAC HOT 1
- Skew-fit gaussian_identity_variance
- AWAC doesn't profit from offline data HOT 4
- IQL: make checkpoints public
- Could someone provide right environment installation procedure? HOT 4
- Python3.5 is not suitable for this project! HOT 1
- Why I could not see result file๏ผ
- SAC log_alpha different from paper HOT 1
- IQL results different with the paper
- Reproduce and create figures results in AWAC.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rlkit.