Table of Contents - [Compatible Agents](<#compatible-agents>) --- # Agent Modules Agents are designed to apply a decision making policy on what actions are best in a given state. ## Compatible Agents | **Author** | **Agent Name** | **Input Code** | **Description** | |:--------------------------- |:---------------------------------- |:-------------- |:-------------------------------------------- | | **elsciRL** | Tabular Q-Learning | *Qlearntab* | *The simplest agent as described by Sutton.* | | | Deep-Q Network | *neural* | *A simple neural agent.* | | **OpenAI StableBaselines3** | Deep-Q Network | *SB3-DQN* | *Application of...* | | | Actor Critic (A2C) | *SB3-A2C* | *Application of...* | | | Proximal Policy Optimization (PPO) | *SB3-PPO* | *Application of...* |