internrl's People
internrl's Issues
DQN in Pytorch
Implement DQN in Pytorch
Use YAML for configurations
Put configurations in a file is neat.
Random initialization instead of zero initialization
Random initialization for discrete state / action values to replace Exploring start.
Add Double DQN to DQN implementation
DQN: Y = r + gamma * max(Q'(s'))
Double DQN: Y = r + gamma * Q'(s', argmax(Q(s')))
Replace main program
Since the program is configured by YAML, it is not necessary to have a scripts folder.
Target network update
Network updates with number of steps rather than epochs
Synchronous update
Synchronous update of PI and VI
Gym env wrapper
Construct our own API to avoid using Gym API
Python 3 Type Hint
Env description
Show env key stats in logger
No n in Box object
Current state and action dimension does not support Box type (in RLAgents/core.py)
Parameter settings
Set parameters from external sources.
optimizer, learning_rate, verbose
DDPG in TensorFlow Keras
eval
eval is a Python keyword. Need to change it.
Logger for main program
Configurations need logger.
Add support of VI, SARSA, QL
Pytest
Use Pytest to test programs
Learning Evaluation
Use Average Q (V) instead of Average cumulative reward for learning evaluation
Relative import vs Absolute import
Network YAML configuration
Construct networks from YAML file.
Pass configurations directly to submodules
Decoding cfg in the main program doesn't seem to be efficient and tidy.
Reorganize main program
Currently main program has redundant part for different agents.
Create a random agent as the baseline of baseline
DQN in TensorFlow Keras
Implement DQN in TensorFlow Keras
Use regular expression to parse logs
So the asyncronous evaluation does not depend on number the position.
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.