bmazoure / driml Goto Github PK
View Code? Open in Web Editor NEWCode for Deep Reinforcement and InfoMax Learning (Neurips 2020)
Code for Deep Reinforcement and InfoMax Learning (Neurips 2020)
Cloned the repo, and ran python main.py --lambda_LL "0" --lambda_GL "0" --lambda_LG "0" --lambda_GG "1" --experiment-name "test" --env-name "procgen-bigfish-v0.500" --n_step-return "7" --nce-batch-size "256" --horizon "10000" --algo "c51" --n-cpus "8" --n-gpus "1" --weight-save-interval "-1" --n_step-nce "-2" --frame_stack "3" --nce_loss "InfoNCE_action_loss" --log-interval-steps=1000 --mode "serial"
as given in the README.md
Runs into the following type error: TypeError: seed() takes 1 positional argument but 2 were given
Here's the complete stack trace: Traceback (most recent call last):
File "main.py", line 223, in
config=config
File "main.py", line 176, in build_and_train
runner.train()
File "/home/hari/Desktop/Hari//MILA/rlpyt/rlpyt/runners/minibatch_rl.py", line 301, in train
n_itr = self.startup()
File "/home/hari/Desktop/Hari//MILA/rlpyt/rlpyt/runners/minibatch_rl.py", line 81, in startup
world_size=world_size,
File "/home/hari/Desktop/Hari/MILA/rlpyt/rlpyt/samplers/serial/sampler.py", line 46, in initialize
set_envs_seeds(envs, seed) # Random seed made in runner.
File "/home/hari/Desktop/Hari/MILA/rlpyt/rlpyt/utils/seed.py", line 61, in set_envs_seeds
env.seed(seed + i)
File "/home/hari/anaconda3/envs/RAD/lib/python3.7/site-packages/gym/core.py", line 241, in seed
return self.env.seed(seed)
File "/home/hari/anaconda3/envs/RAD/lib/python3.7/site-packages/gym/core.py", line 241, in seed
return self.env.seed(seed)
TypeError: seed() takes 1 positional argument but 2 were given
Seems to be a bug in the codebase unless I'm mistaken. Any thoughts as to how I may resolve this is appreciated.
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.