Parallel SAC

In this notebooks, we train a policy that outputs acceleration and message using parallel-SAC.

🟧 + 🔵 -> 🔶 + 🟠

• Parallel SAC with MLP
  • Floating-point message, without reward sharing
  • Floating-point message, with reward sharing
  • Binary message, with reward sharing
  • Summary
• Distributed policy with comm trained using parallel SAC: split model
  • Alternate Action and Communication training