Comments (4)
The reward is computed exactly as log of discriminator, as shown in this line:
Line 99 in d94e147
from pytorch-rl.
The reward is computed exactly as log of discriminator, as shown in this line:
Line 99 in d94e147
This is exactly how the reward should be calculated, however everywhere it is written as the expectation of the derivative of the log term (See above images). Can you please tell me why the 'minus' sign is removed in the expectation term?
The D in this code is actually equivalent to the minus D in the original paper.
Lines 125 to 126 in d94e147
From the above two lines of code, it can be seen that the discriminator's update goal is to output 1 for the generated data g_o
and 0 for the expert data e_o
. The goal of the policy update should then be to minimize the output of the discriminator, i.e., to maximize the -log(D(g_o))
reward, which makes the so-called adversarial training.
from pytorch-rl.
Thank you for your response. For anyone else also wondering the same thing. Please check this line as well:
Line 42 in d94e147
from pytorch-rl.
The reward is computed exactly as log of discriminator, as shown in this line:
Line 99 in d94e147
This is exactly how the reward should be calculated, however everywhere it is written as the expectation of the derivative of the log term (See above images). Can you please tell me why the 'minus' sign is removed in the expectation term?
from pytorch-rl.
Related Issues (20)
- question about A2C
- GAIL discriminator loss uses complete expert data in each iteration? HOT 4
- is this an error:num_steps += (t + 1) ? HOT 1
- about the kl HOT 3
- Question on multiprocessing HOT 1
- Doubt regarding the calculation of advantage HOT 2
- Mountain Car
- Various questions? HOT 1
- Implementation problem HOT 6
- Fail to train of GAIL in Ant-v2 environment HOT 3
- Is this repository only work for Gym Environments?
- What's Conjugate gradients and line_search in TROP?
- What's Conjugate gradients and line_search in TRPO? HOT 1
- About computing Hessian*vector
- A question bout PPO implementation
- Is the implelented performance comparable with the results provided in original GAIL paper?
- TRPO,Is fixed_log_probs the same as log_probs HOT 1
- Why does GAIL get lower rewards the more it is trained? HOT 1
- Failed on " HopperEnv' object has no attribute 'seed' "
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 pytorch-rl.