Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Invalid arguments / not a number error #8

Open
rracinskij opened this issue Jun 1, 2016 · 1 comment
Open

Invalid arguments / not a number error #8

rracinskij opened this issue Jun 1, 2016 · 1 comment

Comments

@rracinskij
Copy link

Hello,
while trying to test the package I get a following error in test.lua:

/usr/local/bin/luajit: invalid element (not a number) at /tmp/luarocks_torch-scm-1-5698/torch7/generic/Tensor.c:141
stack traceback:
[C]: at 0x05e75010
[C]: in function 'Tensor'
./deepqlearn.lua:320: in function 'backward'
torch7-qlearn-test01.lua:28: in main chunk
[C]: in function 'dofile'
/usr/local/lib/luarocks/rocks/trepl/scm-1/bin/th:131: in main chunk
[C]: at 0x0105d66930

A simple script with a single forward/backward loop and scalar as a reward gives the same error message after 4 backward calls. However, changing the reward into a tensor(1) results in an error after four backward calls:

/usr/local/bin/luajit: invalid element (not a number) at /tmp/luarocks_torch-scm-1-5698/torch7/generic/Tensor.c:141
stack traceback:
[C]: at 0x05e75010
[C]: in function 'Tensor'
./deepqlearn.lua:320: in function 'backward'
torch7-qlearn-test01.lua:28: in main chunk
[C]: in function 'dofile'
/usr/local/lib/luarocks/rocks/trepl/scm-1/bin/th:131: in main chunk
[C]: at 0x0105d66930

State is a table, e.g. {1,1}, reward is either a scalar or tensor(1). I'd greatly appreciate any advice on this issue.

@rracinskij
Copy link
Author

Update: the deepqlearn.moon code compiled into lua works without errors.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant