Comments (5)
Note that your are dividing twice through the batch size when computing the update for the actor weights.
1 q_gradient_batch = self.critic_network.gradients(state_batch,action_batch_for_gradients)/BATCH_SIZE
in ddpg.py
2 self.parameters_gradients = tf.gradients(self.action_output,self.parameters,-self.q_gradient_input/BATCH_SIZE)
in actor.py
This might be the cause of your bad performance.
from ddpg.
Hi,
Did you manage to improve the performances by correcting this ? Because even if i do not see any other error in the code, it does not work.
from ddpg.
Still embedding this into a bigger project. I can probably give you feedback if its working or not in a week or so.
Could you elaborate what it not working out? Does the networks converge?
Btw: Note that in the original paper the critic has a learning rate of 0.001 while the author is using 0.0001.
from ddpg.
The paper suggests using batch-norm ("We also report results with components of our algorithm (i.e. the target network or batch normalization) removed. In order to perform
well across all tasks, both of these additions are necessary. "). See Figure 2 in https://arxiv.org/pdf/1509.02971.pdf
from ddpg.
Have fixed bugs and added batch norm on the actor network!
from ddpg.
Related Issues (18)
- run env HumanoidStandup-v1 error HOT 1
- Bug with FilteredEnv
- error: python gym_ddpg.py
- the dimension of Input and Output
- fatal error
- Action used for gradient calculation HOT 2
- Normalize actor gradients? HOT 1
- No target networks in the implementation HOT 1
- DDPG Actor output saturate
- how to save the actor and critic weights
- Error: No module named utlility HOT 2
- Issue about Segmentation fault (core dumped) HOT 1
- mistake found
- Actions generated by Actor network increases to 1. and stay there HOT 1
- X Error of failed request: BadRequest (invalid request code or no such operation)
- How to train DDPG agent on Reacher-v1 env?
- AttributeError: 'FilteredEnv' object has no attribute 'monitor' 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 ddpg.