Poojan Gandhi's Projects
Implement value iteration and policy iteration for the Frozen Lake environment from OpenAI Gym
Implementation of ATM machine using ESP32 and Telegram Bots
This project attempts to use Reinforcement Learning to train a model to perform simple maneuvers, plan navigation and avoid dynamic obstacles.
Solving the gym Pendulum-v0 environment using Policy Gradient method
Implementation of different Tabular and Deep Reinforcement Learning Algorithms on various Gym Environments.
Frozen Lake
Extending the Gym interface for a 2D multi-agent survival RL environment, with communication and team switching
This project attempts to use Reinforcement Learning to train a model to perform various control task on a manipulator.
MNIST Digit Classifier using ANN and CNN
Config files for my GitHub profile.
Solving Snake AI game using Tabular RL Methods