PyTorch 1.x Reinforcement Learning Cookbook

How to do it...

We solve the continuous Mountain Car problem using continuous A2C as follows:

1. Import all the necessary packages and create a continuous Mountain Car instance:

>>> import gym>>> import torch>>> import torch.nn as nn>>> import torch.nn.functional as F>>> env = gym.make('MountainCarContinuous-v0')

2. Let's start with the actor-critic neural network model:

>>> class ActorCriticModel(nn.Module): ...     def __init__(self, n_input, n_output, n_hidden): ...         super(ActorCriticModel, self).__init__() ...         self.fc = nn.Linear(n_input, n_hidden) ...         self.mu = nn.Linear(n_hidden, n_output) ...         self.sigma = nn.Linear(n_hidden, n_output) ...         self.value = nn.Linear(n_hidden, 1) ...         self.distribution = torch.distributions.Normal ... ... def forward(self, ...