GPUCodeForces/S1/uucoco_#91/ImitationLearningLoss_torch.py

25 lines
547 B
Python

import torch
import torch.nn as nn
class Model(nn.Module):
def __init__(self):
super(Model, self).__init__()
def forward(self, pred_actions: torch.Tensor, expert_actions: torch.Tensor) -> torch.Tensor:
loss = ((pred_actions - expert_actions) ** 2).mean()
return loss
batch_size = 32
action_dim = 4
def get_inputs():
pred_actions = torch.randn(batch_size, action_dim)
expert_actions = torch.randn(batch_size, action_dim)
return [pred_actions, expert_actions]
def get_init_inputs():
return []