christian-m02 Goto Github PK

followers: 0.0 following: 9.0 repos: 7.0 gists: 1.0

Name: christian-m02

Type: User

Location: The Hague, Netherlands

christian-m02's Projects

alphalens

Performance analysis of predictive (alpha) stock factors

research_public

Quantitative research and educational materials

udacity-deep-rl-project-1-navigation

Train a deep reinforcement learning agent to navigate a large square world and collect yellow bananas while avoiding blue ones. Uses DQN, Double DQN and Dueling DQN.

udacity-deep-rl-project-2-continuous-control

In the Reacher environment, a double-jointed arm can move to target locations. A reward is provided for each step that the agent's hand is in the goal location. So the task of this project is to train an agent to maintain its position at the target location for as many time steps as possible.

udacity-deep-rl-project-3-collab-compet

In the Tennis environment, two agents control rackets to bounce a ball over a net. If an agent hits the ball over the net, it receives a reward of +0.1. If an agent lets a ball hit the ground or hits the ball out of bounds, it receives a reward of -0.01. So the goal of this project is to train a multi-agent RL Agent to keep the ball in play.