This repo showcases my work exploring different algorithms of RL and their applications.
-
This tutorial discusses the ICM model as an example of curiosty-driven learning specifically for the mountain car probelm. Read more on my medium post Curiosity-Driven Learning with OpenAI and Keras. Or find the full python code here.
-
This tutorial introduces policy gradient algorithms and provides a keras implementation of a deep REINFORCE model. Read more on my medium post Policy Gradient Reinforcement Learning with Keras. Or find the full python code here.
-
The first project of the Udacity deep-RL course focuses on value-based algorithms. Here, I solve the Unity Banana-Navigation task using DQN and PyTorch. See the full python code with accompanying explanations here.
-
The second project of the Udacity deep-RL course focuses on policy-based algorithms. Here, I solve the Unity reacher environment using PPO and PyTorch. See the full python code with accompanying explanations here.
-
The thirds project of the Udacity deep-RL course focuses on mutli-agent learning algorithms. Here, I solve the Unity Tennis environment using DDPG and PyTorch. See the full python code with accompanying explanations here.