Actor-Critic-RL-for-LunarLanderV2

Advantage Actor Critic Algorithm

Implementation of Policy-Gradient and Actor Critic Reinforcement Learning Paradign for LunarLander Simulation of OpenAI Gym:
(1) REINFORCE Policy Gradient Algorithm
(2) Advantage Actor Critic Algorithm (A2C)


Experimental Results:

(1) REINFORCE Policy Gradient Algorithm

(2) Advantage Actor Critic Algorithm (A2C)

(3) Combined REINFOCE vs A2C