deep-rl-agent-solves-unity-reacher | repo solves the 'Reacher ' environment as part of Udacity

deep-rl-agent-solves-unity-reacher is a Python library. deep-rl-agent-solves-unity-reacher has no bugs, it has no vulnerabilities, it has build file available and it has low support. However deep-rl-agent-solves-unity-reacher has a Non-SPDX License. You can download it from GitHub.

This repo solves the 'Reacher' environment as part of Udacity's Deep Reinforcement Nanodegree. In this environment, a double-jointed arm can move to target locations. A reward of +0.1 is provided for each step that the agent's hand is in the goal location. Thus, the goal of your agent is to maintain its position at the target location for as many time steps as possible. The observation space consists of 33 variables corresponding to position, rotation, velocity, and angular velocities of the arm (continuous state space). Each action is a vector with four numbers (continuous action space), corresponding to torque applicable to two joints. Every entry in the action vector should be a number between -1 and 1.