lifelong-ml / mendez2022modularlifelongrl Goto Github PK
View Code? Open in Web Editor NEWSource code to reproduce experiments from Mendez et al., ICLR '22
License: Apache License 2.0
Source code to reproduce experiments from Mendez et al., ICLR '22
License: Apache License 2.0
Hi,
I already follow the setup instruction but I had an error when trying to run this code:
python -m experiments.ppo_minigrid_lifelong --algo comp-ppo --learning-rate 1e-3 --steps-per-proc 256 --batch-size 64 --procs 16 --num-tasks 64 --num-steps 1000000 --max-modules 4
This is the error that I get:
Traceback (most recent call last):
File "/home/user/anaconda3/envs/modcrl/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/home/user/anaconda3/envs/modcrl/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/user/Reinfocement Learning/modcrl/Mendez2022ModularLifelongRL/Discrete2D/torch-ac-composable/torch_ac_composable/experiments/ppo_minigrid_lifelong.py", line 233, in
eval_episodes=eval_episodes,
File "/home/user/Reinfocement Learning/modcrl/Mendez2022ModularLifelongRL/Discrete2D/torch-ac-composable/torch_ac_composable/algos/agent_wrappers.py", line 467, in train
exps, logs1 = self.agent.collect_experiences(task_id)
File "/home/user/Reinfocement Learning/modcrl/Mendez2022ModularLifelongRL/Discrete2D/torch-ac-composable/torch_ac_composable/algos/base.py", line 180, in collect_experiences
dist, value = self.acmodel(preprocessed_obs, task_id)
File "/home/user/anaconda3/envs/modcrl/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/user/Reinfocement Learning/modcrl/Mendez2022ModularLifelongRL/Discrete2D/torch-ac-composable/torch_ac_composable/models/acmodel_modular_fixed.py", line 156, in forward
x = self.fc(features, task_id, return_bc)
File "/home/user/Reinfocement Learning/modcrl/Mendez2022ModularLifelongRL/Discrete2D/torch-ac-composable/torch_ac_composable/models/acmodel_modular_fixed.py", line 145, in fc
x_actor = self.actor_layersself.agent_dyn_dict[task_id]
File "/home/user/anaconda3/envs/modcrl/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/user/anaconda3/envs/modcrl/lib/python3.6/site-packages/torch/nn/modules/container.py", line 100, in forward
input = module(input)
File "/home/user/anaconda3/envs/modcrl/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "/home/user/anaconda3/envs/modcrl/lib/python3.6/site-packages/torch/nn/modules/linear.py", line 87, in forward
return F.linear(input, self.weight, self.bias)
File "/home/user/anaconda3/envs/modcrl/lib/python3.6/site-packages/torch/nn/functional.py", line 1610, in linear
ret = torch.addmm(bias, input, weight.t())
RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)
Is there something that I missed? Thank you.
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.