Can't run trained policy because there's an issue with loading the models.

rail-berkeley / rlkit

Collection of reinforcement learning algorithms

MIT License

2.45k stars 550 forks source link

Can't run trained policy because there's an issue with loading the models. #103

Closed MhmdGaffar closed 4 years ago

MhmdGaffar commented 4 years ago

this is the error I got: RuntimeError: Expected object of type torch.cuda.FloatTensor but found type torch.FloatTensor for argument #4 'mat1' I am running the ddpg example with ptu.set_gpu_mode(True) what can I do?