Yeshwant Dattatreya yeshwantd

## gist:93ad6f62cd78f9edb6788679d7138773
# Soft Actor-Critic (SAC) for Humanoid-v5

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.distributions import Normal

import copy
import numpy as np

## gist:564162e91c644205c8de274ff104418a
# Soft Actor-Critic (SAC)

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.distributions import Normal

import copy
import numpy as np

## policy_gradient_with_disciounted_rewards.py
import gymnasium as gym
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.distributions import Categorical
import numpy as np

class Policy(nn.Module):
    def __init__(self):
        super(Policy, self).__init__()

## policy_gradient_1.py
import gymnasium as gym
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.distributions import Categorical
import numpy as np

class Policy(nn.Module):
    def __init__(self):
        super(Policy, self).__init__()
	# Soft Actor-Critic (SAC) for Humanoid-v5

	import torch
	import torch.nn as nn
	import torch.nn.functional as F
	import torch.optim as optim
	from torch.distributions import Normal

	import copy
	import numpy as np
	# Soft Actor-Critic (SAC)

	import torch
	import torch.nn as nn
	import torch.nn.functional as F
	import torch.optim as optim
	from torch.distributions import Normal

	import copy
	import numpy as np
	import gymnasium as gym
	import torch
	import torch.nn as nn
	import torch.nn.functional as F
	from torch.distributions import Categorical
	import numpy as np

	class Policy(nn.Module):
	def __init__(self):
	super(Policy, self).__init__()