SimDRLSR v0.1

Reinforcement Learning atributes:

• 4 agent actions:

  • wait;
  • look;
  • handwave;
  • handshake.

• 3 reward types:

  • Fail handshake: -0.1 (adjustable);
  • Successful handshake: 1 (adjustable);
  • Neutral: 0.

• States:

  • 8 sequential grayscale images;
  • 8 sequential depth images.