henry-prior / jax-rl Goto Github PK
View Code? Open in Web Editor NEWJAX implementations of core Deep RL algorithms
License: MIT License
JAX implementations of core Deep RL algorithms
License: MIT License
Hi,
Thanks so much for the clean implementation. In MPO, using actor_log_prob.transpose((0, 1)) causes error.
Line 236 in a2c6067
TypeError: transpose permutation isn't a permutation of operand dimensions, got permutation (0, 1) for operand shape (256, 20, 1).
I checked the shape of actor_log_prob and weights, they are in the same shape. After removing this line, I can get the samilar performance in cartpole_swingup env as shown in README.md.
Best,
Yi
When running the code I get:
AttributeError Traceback (most recent call last)
/tmp/ipykernel_49/2609719913.py in
6
7 temp_timestep = env.reset()
----> 8 state_dim = flat_obs(temp_timestep.observation).shape[0]
9 action_dim = env.action_spec().shape[0]
10 max_action = float(env.action_spec().maximum[0])
AttributeError: 'DeviceArray' object has no attribute 'observation'
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.