Pinned Repositories
Rainbow-Deep-Q-Network-Reinforcement-Learning-Bananna-Environment
This repo is for my progressive implementation of the full rainbow DQN algorithm, which comprises 6 modifications over DQN which are together considered state-of-the-art in the field. The training environment is the Unity Banana environment provided for the Udacity deep reinforcement learning nanodegree.
DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment
This repo demonstrates the usage of an actor-critic setup via the deep-deterministic-policy-gradients algorithm. The environment to be solved is the Unity Reacher Environment provided in the Udacity Deep Reinforcement Learning nanodegree
Distributional-Multi-Agent-Actor-Critic-Reinforcement-Learning-MADDPG-Tennis-Environment
The state-of-the-art in multi-agent Reinforcement Learning is the MADDPG algorithm which utilises DDPG actor-critic neural networks where each agent uses centralized critic training but decentralized actor execution, and is capable of learning either cooperative or competitive environments. This is demonstrated on the Unity Tennis Environment.
rainbow-is-all-you-need
Rainbow is all you need! Step-by-step tutorials from DQN to Rainbow
deep-reinforcement-learning-1
Repo for the Deep Reinforcement Learning Nanodegree program
Remtasya's Repositories
Remtasya/Rainbow-Deep-Q-Network-Reinforcement-Learning-Bananna-Environment
This repo is for my progressive implementation of the full rainbow DQN algorithm, which comprises 6 modifications over DQN which are together considered state-of-the-art in the field. The training environment is the Unity Banana environment provided for the Udacity deep reinforcement learning nanodegree.
Remtasya/Distributional-Multi-Agent-Actor-Critic-Reinforcement-Learning-MADDPG-Tennis-Environment
The state-of-the-art in multi-agent Reinforcement Learning is the MADDPG algorithm which utilises DDPG actor-critic neural networks where each agent uses centralized critic training but decentralized actor execution, and is capable of learning either cooperative or competitive environments. This is demonstrated on the Unity Tennis Environment.
Remtasya/rainbow-is-all-you-need
Rainbow is all you need! Step-by-step tutorials from DQN to Rainbow
Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment
This repo demonstrates the usage of an actor-critic setup via the deep-deterministic-policy-gradients algorithm. The environment to be solved is the Unity Reacher Environment provided in the Udacity Deep Reinforcement Learning nanodegree
Remtasya/deep-reinforcement-learning-1
Repo for the Deep Reinforcement Learning Nanodegree program