0.2.2 1.4.0 3.7.3 (default, Mar 27 2019, 22:11:17)
[GCC 7.3.0] linux
problem:
UserWarning: Using a target size (torch.Size([128, 4])) that is different to the input size (torch.Size([128, 1]))
Seems the shape of current_q1 and current_q2 is not correct.
python3 examples/halfcheetahBullet_v0_sac.py --task BipedalWalkerHardcore-v3 --run-id train
Epoch #1: 0%| | 0/1000 [00:00<?, ?it/s]
/usr/local/lib/python3.6/site-packages/tianshou/policy/modelfree/sac.py:111: UserWarning: Using a target size (torch.Size([128, 4])) that is different to the input size (torch.Size([128, 1])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.
critic1_loss = F.mse_loss(current_q1, target_q)
/usr/local/lib/python3.6/site-packages/tianshou/policy/modelfree/sac.py:117: UserWarning: Using a target size (torch.Size([128, 4])) that is different to the input size (torch.Size([128, 1])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size.
critic2_loss = F.mse_loss(current_q2, target_q)
UserWarning: Using a target size (torch.Size([128, 4])) that is different to the input size (torch.Size([128, 1]))
Seems the shape of current_q1 and current_q2 is not correct.