Skip to content

Latest commit

 

History

History
15 lines (10 loc) · 561 Bytes

README.md

File metadata and controls

15 lines (10 loc) · 561 Bytes

Here is my implementation of popular RL algorithms. I referred many popular code bases while writing my implementations.

The algorithms I have implemented are -

  1. DQN
  2. PPO
  3. DDQN
  4. PG (Work needed)
  5. DDPG (Work needed)
  6. SAC (Work needed)

Trained Agents -

Pong       Breakout