Comments (8)
me too
from rsl_rl.
Can confirm I've experienced it too. In my case, I had introduced some sparse rewards to my environment. Not sure that's the cause tho.
from rsl_rl.
Same problem here. When visualizing the training data in tensorboard, I notice that Loss/value_function suddenly goes to infinity
from rsl_rl.
Same problem
from rsl_rl.
When facing the error std>=0, check the output 'Value Function Loss' to see whether it's inf or not. If it is inf, there is a solution that you can try. Based on the knowledge from issues ray-project/ray#19291 with the fix ray-project/ray#22171 and ray-project/ray@ddd1160, the codes starting at L159 in ppo.py file of rsl_rl (version 2.0.2) need to be modified as follows:
When facing the error std>=0, check the output 'Value Function Loss' to see whether it's inf or not. If it is inf, there is a solution that you can try. Based on the knowledge from issues ray-project/ray#19291 with the fix ray-project/ray#22171 and ray-project/ray@ddd1160, the codes starting at L159 in ppo.py file of rsl_rl (version 2.0.2) need to be modified as follows:
Thanks for your answer, I'll try it out
from rsl_rl.
When facing the error std>=0, check the output 'Value Function Loss' to see whether it's inf or not. If it is inf, there is a solution that you can try. Based on the knowledge from issues ray-project/ray#19291 with the fix ray-project/ray#22171 and ray-project/ray@ddd1160, the codes starting at L159 in ppo.py file of rsl_rl (version 2.0.2) need to be modified as follows:
from rsl_rl.
When facing the error std>=0, check the output 'Value Function Loss' to see whether it's inf or not. If it is inf, there is a solution that you can try. Based on the knowledge from issues ray-project/ray#19291 with the fix ray-project/ray#22171 and ray-project/ray@ddd1160, the codes starting at L159 in ppo.py file of rsl_rl (version 2.0.2) need to be modified as follows:
Note this kind of method may not work and it may reduce the learning speed. I've tested it using parameters 'iteration : 30000' & 'num_envs : 12000 to 30000' for training my own robot. The training process randomly failed between 1,000 and 18,000 iterations. I've checked the 'value batch' and 'return batch'. Once the training failed, these two values showed very large positive or negative numbers. I ultimately completed the entire training process by modifying the reward and penalty. Since I'm still fresh to the RL, I don't know exactly what happened. By the way, I've tested modifying the hyperparameters of PPO and the structure of networks. It didn't work. I would greatly appreciate it if someone could provide some information on this topic.
There is an unsuitable method to ensure the training proceeds. When std >= 0 and the Value Function Loss shows inf, you can first adjust some parameters in the project and then use --resume to load the checkpoint and continue training.
from rsl_rl.
Adding code actions = torch.clip(actions, min=-6.28, max=6.28) before env.step(actions) seems to help. And it is better to add a penalty to actions to prevent the actor model from outputting too large values.
from rsl_rl.
Related Issues (20)
- There is an error with installation
- Wrong ETA for resumed trainings
- Where to find get_observations(self) -> torch.Tensor HOT 1
- RNN padding bug fix HOT 1
- Performance drop when resumed training with the empirical normalization HOT 1
- time out bootstrapping possible bug.
- How to uninstall rsl_rl and install v1.0.2? HOT 2
- Benchmarking on the new implemented algorithms
- Is rsl_rl v2.0.x supporting legged_gym? HOT 1
- mini_batch_generator, same indice in different epoch
- Saving code diff fails if code contains non-utf characters like °
- Request to add symmetric data augmentation
- Need Base Velocity of Unitree Go2 for Policy Observations
- Observation and Action Transformations for Policy Deployment on UnitreeGo2
- Huge performance gaps between algorithms and master on base IsaacLab tasks HOT 1
- Citation HOT 1
- Error while training with legged_gym HOT 3
- action noise parameterization HOT 1
- error HOT 1
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 rsl_rl.