ru-automated-reasoning-group / pi-prl Goto Github PK
View Code? Open in Web Editor NEWICLR'22 Programmatic Reinforcement Learning
License: MIT License
ICLR'22 Programmatic Reinforcement Learning
License: MIT License
Hello! I'm trying to run the example in the README by running "python3 pi_PRL.py". However I got error like
not enough values to unpack (expected 5, got 4)
Timeout Error raised... Trying again
Traceback (most recent call last):
File "pi_PRL.py", line 664, in <module>
plot_keys=['stoc_pol_mean', 'running_score'])
File "/home/wyx/Documents/Analogy/code/pi-PRL/mjrl/utils/train_agent.py", line 153, in train_agent_flip
stats = agent.train_step(**args)
File "/home/wyx/Documents/Analogy/code/pi-PRL/mjrl/algos/batch_reinforce.py", line 84, in train_step
paths = trajectory_sampler.sample_paths(**input_dict)
File "/home/wyx/Documents/Analogy/code/pi-PRL/mjrl/samplers/core.py", line 144, in sample_paths
for result in results:
TypeError: 'NoneType' object is not iterable
Would you like to help me with that?
And I also noticed that if I run the code directly, I'll get error like
'numpy.random._generator.Generator' object has no attribute 'randn'
I tried to fix it by substitute all "self.np_random" by "np.random". Maybe this cause the first error. Would you like to share with me the numpy version you used in the project?
Hello,
I have a question about the results that you obtained with LunarLander-v2 in the appendix of the paper. Specifically, I want to know about the criteria used for selecting observations with PID controller. Were all observations utilized, or was there a specific method for their selection in the LunarLander task?
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.