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.
Master Snake Game AI with PPO: Step-by-Step Guide (Part I)
This is first of two part tutorial. Here we learn to build snake game. In part two, we will learn to build a PPO agent to play with it.
PPO Implementation in PyTorch
In this blog post, we will explore the Proximal Policy Optimization (PPO) algorithm. We’ll compare it to other deep reinforcement learning algorithms like Double Deep Q-learning and TRPO. Additionally, we’ll learn how to implement PPO using PyTorch.
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.
Understanding Implicit Quantile Networks in Reinforcement Learning
IQN is a state-of-the-art RL algorithm that focuses on predicting the full distribution of returns rather than just the mean. This approach provides a more comprehensive understanding of the value of actions, allowing for better decision-making in uncertain environments
Double DQN For Lunar Lander With PyTorch
In this blog post, we will implement Double DQN using PyTorch to solve the Lunar Lander environment from OpenAI Gym.
Acrobot-ing with Actor Critic
Solving the Acrobot problem with the help of Actor-Critic algorithm.
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 […]
Q-Taxi
Introduction There are four designated locations in the grid world indicated by R(ed), G(reen), Y(ellow), and B(lue). When the episode starts, the taxi starts off at a random square and the passenger is at a random location. The taxi drives to the passenger’s location, picks up the passenger, drives to the passenger’s destination (another one of the four specified locations), […]
Exploration vs Exploitation
A colony of bees knows a garden of roses nearby. This garden is their primary source of nectar and pollen. There might be another garden far from their hive which might contain a variety of flowers. Going to that garden demands a lot of time and energy. Should this colony of bees continue bringing nectar and pollen from nearby rose […]
Frozen Lake meets Value Iteration
The Frozen Lake This lake has a 4×4 grid of total 16 states. # Frozen Lake Gridworld: It is highly stochastic environment (33.33% action success, 66.66% split evenly in right angles) It contains 4×4 grid, 16 states (0-15) The agent gets +1 for landing in state 15 (right bottom corner) 0 otherwise The states 5, 7, 11, and 12 are […]