A comprehensive beginner-friendly library implementing popular RL and DRL Algorithms focused on teaching the implementation strategies.

1. Deep-Q Networks (DQN) : A Pytorch implementation of a simple DQN algorithm modularized to easily incorporate algorithmic changes in the agent-environment, neural network model, and other trainable parameters.
2. Advantage Actor-Critic (A2C) : Pytorch implementation of a simple A2C algorithm.
3. Proximal Policy Optimization (PPO-Clip): Pytorch implementation of a simple PPO algorithm (Clip version).