qfettes / curiositydrivenexplorationbyselfsupervisedprediction Goto Github PK
View Code? Open in Web Editor NEWReproduction of Curiosity-driven Exploration by Self-supervised Prediction in PyTorch
License: MIT License
Reproduction of Curiosity-driven Exploration by Self-supervised Prediction in PyTorch
License: MIT License
Hi, I am trying to train the code, but it appeared this issue.
Traceback (most recent call last):
File "a2c_devel.py", line 381, in
train(config)
File "a2c_devel.py", line 299, in train
last_reward_logged = tb_plot_from_monitor(writer, log_dir, np.mean(config.adaptive_repeat), last_reward_logged, 'episode length')
File "D:\ICM\utils\plot.py", line 420, in tb_plot_from_monitor
x, y = load_raw_eplength_data(log_dir, 1, 1) #load data
File "D:\ICM\utils\plot.py", line 395, in load_raw_eplength_data
t_time = float(tmp[2])
IndexError: list index out of range
Could you tell me how to fix this problem? Thanks
Hi,
your code can run but it would have an error when debugging as follows:
'UnicodeDecodeError: 'utf-8' codec can't decode bytes in position 1022-1023: unexpected end of data.'
And in the 'ICM_A2C.py', the loss only consists of forward loss and inverse loss like this: 'total_forward_loss + total_inverse_loss'. However, the loss defined in the paper including other loss.
Could you give me some advice. Thank you for your reply.
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.