Bipedal Walker with PPO: A Step-by-Step Guide to Solving the RL Challenge
In this tutorial we will learn how to master a Bipedal Walker with PPO (Proximal Policy Optimization).
Master Snake Game AI with PPO: Step-by-Step Guide (Part II)
Second Part we will learn about the major components PPO for ai agent.
Prioritized Experience Replay Using PyTorch
Introduction of Prioritized Experience Replay and its implementation with PyTorch.
Policy Gradient Implementation Using PyTorch
This is an implementation of Policy Gradient algorithm using PyTorch.
Gaussian Double Deep Q Learning
Implementation of Gaussian Double Deep Q network with PyTorch
MoG-DQN Implementation In PyTorch To Solve Lunar Lander
This is implementation of MoG-DQN using PyTorch.
Acrobot-ing with Actor Critic
Solving the Acrobot problem with the help of Actor-Critic algorithm.
CNN and its friends in PyTorch
The blog about the CNN functions in PyTorch and other assisting functions generally used with Convolution Neural Networks.
Double Deep Q-Network
In double DQNs, we use a separate network to estimate the target rather than the prediction network. The separate network has the same structure as the prediction network. And its weights are fixed for every T episode (T is a hyperparameter we can tune), which means they are only updated after every T episode. The update is simply done by […]
Climbing the Mountain with Neural Network
Function Approximation For problems with very large number of states it will not be feasible for our agent to use table to record the value of all the action for each state and make its policy accordingly. In Function approximation agent learns a function which will approxmately give it best action for particular state. In this example we will use […]
SARSA in the Wind
We will use SARSA algorithm to find the optimal policy so that our agent can navigate in windy world. SARSA State–action–reward–state–action (SARSA) is an algorithm for learning a Markov decision process policy, used in the reinforcement learning area of machine learning. SARSA focuses on state-action values. It updates the Q-function based on the following equation: Q(s,a) = Q(s,a) + α (r + γ Q(s’,a’) – Q(s,a)) Here s’ […]
Balancing pole with Policy Gradient
The policy gradient algorithm trains an agent by taking small steps and updating the weight based on the rewards associated with those steps at the end of an episode. The technique of having the agent run through an entire episode and then updating the policy based on the rewards obtained is called Monte Carlo policy gradient. The action is selected […]
Logistic Regression in PyTorch
Load the Data Converting each column data to numpy array From numpy array to pytorch tensor Plotting the data Using the GPU Defining the neural network Putting neural network on GPU Loss function Setting ADAM as an optimizer Defining accuracy The main loop Plotting Loss Plotting accuracy After one epoch Plots to show performance of neural network over epochs
Basic Neural Network in PyTorch
Making a simple neural network with a single hidden layer and four neurons in hidden layer. Schema of our Neural Network Import necessary libraries Inputs and outputs Converting basic python array to PyTorch tensors Code to use GPU if available Putting our variable to GPU Defining neural network instantiate neural network Weights of different layers Loss function Only one forward […]
PyTorch Tensors
This blog post contains following topics related to tensors: Import Version Declarations item() Zero, identity and linspace Random generator Datatypes Operation with constant Element wise operations Matrix multiplication Matrix inversion Transpose of matrix Determinant of matrix Indexing and slicing Broadcasting Reshape Squeeze and unsqueeze Concatenate and stack Reorganize the data element numpy and pytorch tensor Operations on complex numbers Import […]
2 in One Neural Network
Here we present a 2 in one network. A neural network which does regression and classification at same time. Iris data set has been used in this example Loading the dataset Shuffle the dataframe Inputs and Outputs We take sepal.length, sepal.width and petal.length as an input parameter. We take petal.width as first output parameter and variety as second parameter. The […]
Multi class Classification
We have three classes of images : 7, 8 and 9. The following codes uses VGG16 and CNN to build a model which classifies the images of 7, 8 and 9. Import necessary libraries as usual Load Data: Source of data 7_8_9 Class to load data and make targets Load data and display Vgg16 model Summary of model Function to […]