officium / rl-experiments Goto Github PK
View Code? Open in Web Editor NEWHigh-quality implementations of deep reinforcement learning algorithms for experiments
License: MIT License
High-quality implementations of deep reinforcement learning algorithms for experiments
License: MIT License
Could you specify, whether your PPO is PPO1 or PPO 2. Thank you :)
I've been struggling to find an A2C implementation that learns anything at all on Pong and Breakout.
I forked your repo and hoped it would be different, but for some reason, it doesn't seem to learn anything.
I left all the defaults the same, ran for 3M timesteps, but changed the logging rate to prevent colab from crashing.
https://colab.research.google.com/drive/1oQpgRNUIpTnVlblrm9SMBVxWWDAr75Y-
Could you have a look please :)
Thanks
Could you tell me how to get the results? your's results in log made me puzzled, I haven't met this situation~
Like dueling, atom_number in DQN
A2C in this implementation learn faster than openai's one. All hyper-parameters are the same.
Monitor is implemented at VecEnv
. The right way may make it as a independent wrapper and insert into before ClipReward
wrapper.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.