Closed fatalfeel closed 4 years ago
0.002 (0.9, 0.999) Episode 20 avg length: 85 reward: -228 Traceback (most recent call last): File "/mnt/projects/PPO-PyTorch/PPO.py", line 179, in ppo.update(memory) File "/mnt/projects/PPO-PyTorch/PPO.py", line 122, in update loss.mean().backward() File "/usr/lib/python3.7/site-packages/torch/tensor.py", line 198, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "/usr/lib/python3.7/site-packages/torch/autograd/init.py", line 100, in backward allow_unreachable=True) # allow_unreachable flag RuntimeError: expected dtype Double but got dtype Float (validate_dtype at /pytorch/aten/src/ATen/native/TensorIterator.cpp:143) frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x46 (0x7f3ece1e3536 in /usr/lib/python3.7/site-packages/torch/lib/libc10.so) frame #1: at::TensorIterator::compute_types() + 0xce3 (0x7f3ea23c2a23 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #2: at::TensorIterator::build() + 0x44 (0x7f3ea23c5404 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #3: at::native::mse_loss_backward_out(at::Tensor&, at::Tensor const&, at::Tensor const&, at::Tensor const&, long) + 0x193 (0x7f3ea2212953 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #4: + 0xf903d7 (0x7f3e65d073d7 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cuda.so) frame #5: at::native::mse_loss_backward(at::Tensor const&, at::Tensor const&, at::Tensor const&, long) + 0x172 (0x7f3ea221b092 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #6: + 0xf9068f (0x7f3e65d0768f in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cuda.so) frame #7: + 0x10c2536 (0x7f3ea264b536 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #8: + 0x2a9ecdb (0x7f3ea4027cdb in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #9: + 0x10c2536 (0x7f3ea264b536 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #10: torch::autograd::generated::MseLossBackward::apply(std::vector<at::Tensor, std::allocator >&&) + 0x1f7 (0x7f3ea3e2f777 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #11: + 0x2d89705 (0x7f3ea4312705 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #12: torch::autograd::Engine::evaluate_function(std::shared_ptr&, torch::autograd::Node*, torch::autograd::InputBuffer&) + 0x16f3 (0x7f3ea430fa03 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #13: torch::autograd::Engine::thread_main(std::shared_ptr const&, bool) + 0x3d2 (0x7f3ea43107e2 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #14: torch::autograd::Engine::thread_init(int) + 0x39 (0x7f3ea4308e59 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so) frame #15: torch::autograd::python::PythonEngine::thread_init(int) + 0x38 (0x7f3ed6fa6ac8 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_python.so) frame #16: + 0xc70f (0x7f3ed668770f in /usr/lib/python3.7/site-packages/torch/lib/libtorch.so) frame #17: + 0x76ba (0x7f3edf5e06ba in /lib/x86_64-linux-gnu/libpthread.so.0) frame #18: clone + 0x6d (0x7f3edf31641d in /lib/x86_64-linux-gnu/libc.so.6)
Process finished with exit code 1
fixed use this rewards = torch.tensor(rewards, dtype=torch.float32).to(device)
0.002 (0.9, 0.999) Episode 20 avg length: 85 reward: -228 Traceback (most recent call last): File "/mnt/projects/PPO-PyTorch/PPO.py", line 179, in
ppo.update(memory)
File "/mnt/projects/PPO-PyTorch/PPO.py", line 122, in update
loss.mean().backward()
File "/usr/lib/python3.7/site-packages/torch/tensor.py", line 198, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/usr/lib/python3.7/site-packages/torch/autograd/init.py", line 100, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: expected dtype Double but got dtype Float (validate_dtype at /pytorch/aten/src/ATen/native/TensorIterator.cpp:143)
frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x46 (0x7f3ece1e3536 in /usr/lib/python3.7/site-packages/torch/lib/libc10.so)
frame #1: at::TensorIterator::compute_types() + 0xce3 (0x7f3ea23c2a23 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #2: at::TensorIterator::build() + 0x44 (0x7f3ea23c5404 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #3: at::native::mse_loss_backward_out(at::Tensor&, at::Tensor const&, at::Tensor const&, at::Tensor const&, long) + 0x193 (0x7f3ea2212953 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #4: + 0xf903d7 (0x7f3e65d073d7 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cuda.so)
frame #5: at::native::mse_loss_backward(at::Tensor const&, at::Tensor const&, at::Tensor const&, long) + 0x172 (0x7f3ea221b092 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #6: + 0xf9068f (0x7f3e65d0768f in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cuda.so)
frame #7: + 0x10c2536 (0x7f3ea264b536 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #8: + 0x2a9ecdb (0x7f3ea4027cdb in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #9: + 0x10c2536 (0x7f3ea264b536 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #10: torch::autograd::generated::MseLossBackward::apply(std::vector<at::Tensor, std::allocator >&&) + 0x1f7 (0x7f3ea3e2f777 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #11: + 0x2d89705 (0x7f3ea4312705 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #12: torch::autograd::Engine::evaluate_function(std::shared_ptr&, torch::autograd::Node*, torch::autograd::InputBuffer&) + 0x16f3 (0x7f3ea430fa03 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #13: torch::autograd::Engine::thread_main(std::shared_ptr const&, bool) + 0x3d2 (0x7f3ea43107e2 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #14: torch::autograd::Engine::thread_init(int) + 0x39 (0x7f3ea4308e59 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_cpu.so)
frame #15: torch::autograd::python::PythonEngine::thread_init(int) + 0x38 (0x7f3ed6fa6ac8 in /usr/lib/python3.7/site-packages/torch/lib/libtorch_python.so)
frame #16: + 0xc70f (0x7f3ed668770f in /usr/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame #17: + 0x76ba (0x7f3edf5e06ba in /lib/x86_64-linux-gnu/libpthread.so.0)
frame #18: clone + 0x6d (0x7f3edf31641d in /lib/x86_64-linux-gnu/libc.so.6)
Process finished with exit code 1