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