search

sweetice / Deep-reinforcement-learning-with-pytorch

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
MIT License
3.75k stars 837 forks source link

bug: expected np.ndarray (got tuple) #47

Open zhang-qiang-github opened 1 month ago

zhang-qiang-github commented 1 month ago

state = torch.from_numpy(state).float().unsqueeze(0) report this bug.

The input state is: image

The torch version is: 1.11.0+cu113.

Any suggestion is appreciated~~~