Reacher

In this projects we’ll implementing agents that learns to play Unity Reacher using several Deep Rl algorithms. Unity Ml Agents is a toolkit for developing and comparing reinforcement learning algorithms. We’ll be using pytorch library for the implementation.

Libraries Used

• Unity Ml Agents
• PyTorch
• numpy
• matplotlib

About Enviroment

• Set-up: Double-jointed arm which can move to target locations.
• Goal: The agents must move its hand to the goal location, and keep it there.
• Agents: The environment contains 10 agent with same Behavior Parameters.
• Agent Reward Function (independent):
  • +0.1 Each step agent’s hand is in goal location.
• Behavior Parameters:
  • Vector Observation space: 26 variables corresponding to position, rotation, velocity, and angular velocities of the two arm Rigidbodies.
  • Vector Action space: (Continuous) Size of 4, corresponding to torque applicable to two joints.
  • Visual Observations: None.
• Float Properties: Five
  • goal_size: radius of the goal zone
    • Default: 5
    • Recommended Minimum: 1
    • Recommended Maximum: 10
  • goal_speed: speed of the goal zone around the arm (in radians)
    • Default: 1
    • Recommended Minimum: 0.2
    • Recommended Maximum: 4
  • gravity
    • Default: 9.81
    • Recommended Minimum: 4
    • Recommended Maximum: 20
  • deviation: Magnitude of sinusoidal (cosine) deviation of the goal along the vertical dimension
    • Default: 0
    • Recommended Minimum: 0
    • Recommended Maximum: 5
  • deviation_freq: Frequency of the cosine deviation of the goal along the vertical dimension
    • Default: 0
    • Recommended Minimum: 0
    • Recommended Maximum: 3
• Benchmark Mean Reward: 30

Deep RL Agents

Any questions

If you have any questions, feel free to ask me:

• Mail: deepanshut041@gmail.com
• Github: https://github.com/deepanshut041/Reinforcement-Learning
• Website: https://deepanshut041.github.io/Reinforcement-Learning
• Twitter: @deepanshut041

Don’t forget to follow me on twitter, github and Medium to be alerted of the new articles that I publish

How to help

• Clap on articles: Clapping in Medium means that you really like my articles. And the more claps I have, the more my article is shared help them to be much more visible to the deep learning community.
• Improve our notebooks: if you found a bug or a better implementation you can send a pull request.