htmrl's People
Forkers
ibagurhtmrl's Issues
Trying to reproduce your results
After excecuting:
python run.py config/bandit.yml
I get the following output:
run.py:179: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
yml = yaml.load(stream)
{'general': {'repeats': 1000, 'steps': 10000}, 'env': {'name': 'Bandit', 'k': 10, 'shuffle': 0}, 'algorithms': {'htmrl': {'enabled': 1, 'input_size': 6, 'cell_count': 2048, 'active_count': 40, 'boost_until': 0, 'reward_window': 1000, 'boost_strength': 1.0, 'only_reinforce_selected': 0, 'reward_scaled_reinf': 1, 'normalized_rewards': 1, 'boost_scaled_reinf': 0}, 'eps': {'enabled': 0, 'e': 0.1}}, 'experiments': [{'default': {'algorithms': {'eps': {'enabled': 1}}}}, {'eps001': {'algorithms': {'htmrl': {'enabled': 0}, 'eps': {'enabled': 1, 'e': 0.01}}}}, {'longwindow': {'algorithms': {'htmrl': {'reward_window': 2000}}}}, {'verylongwindow': {'algorithms': {'htmrl': {'reward_window': 10000}}}}, {'small': {'algorithms': {'htmrl': {'cell_count': 100, 'active_count': 10}}}}, {'tiny': {'algorithms': {'htmrl': {'input_size': 1, 'cell_count': 20, 'active_count': 2}}}}, {'noboost': {'algorithms': {'htmrl': {'boost_strength': 0.0}}}}, {'shuffle': {'env': {'shuffle': 1}, 'algorithms': {'eps': {'enabled': 1, 'e': 0.01}}}}]}
{'enabled': 1, 'input_size': 6, 'cell_count': 2048, 'active_count': 40, 'boost_until': 0, 'reward_window': 1000, 'boost_strength': 1.0, 'only_reinforce_selected': 0, 'reward_scaled_reinf': 1, 'normalized_rewards': 1, 'boost_scaled_reinf': 0}
<class 'HTMRL.env.bandit.Bandit'>
<class 'HTMRL.env.bandit.Bandit'>
.
.
.
This repeats a lot...and then:
multiprocessing.pool.RemoteTraceback:
"""
Traceback (most recent call last):
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.7_3.7.2544.0_x64__qbz5n2kfra8p0\lib\multiprocessing\pool.py", line 121, in worker
result = (True, func(*args, **kwds))
File "C:\Users\power\OneDrive\Documentos\HTMRL-master\run.py", line 123, in repeat_algo_reprod
env = env_init(env_config)
NameError: name 'env_init' is not defined
"""
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "run.py", line 232, in
results = repeat_algo(env_init, env_config, steps, repeats, run_htmrl, rawfile, htmrl_config=htmrl)
File "run.py", line 142, in repeat_algo
new_rews = retval.get()[0]
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.7_3.7.2544.0_x64__qbz5n2kfra8p0\lib\multiprocessing\pool.py", line 657, in get
raise self._value
NameError: name 'env_init' is not defined
This only happens in my laptop, when I tried to run the same command in a colab notebook, the only thing I get is:
0
1000
2000
3000
4000
5000
6000
7000
8000
9000
TIMER 37.37249302864075 9999
2040 10
And it repeats again and again, like forever (I left it running like two hours and nothing else happened). Something similar happens with the other three .yml files.
Furthermore, when I click the link you attached in the plots readme, it says the page is not reachable...Would you help me?
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.