Closed BlueDi closed 5 years ago
Improve DeepDip to its final version, v1.
This should be achieved by implementing known improvements to the DQN algorithm such as Dueling Networks, or Prioritized Experience Replay.
The DQN was not used due to incompatibilities explained in #4. ACKTR was implemented and on this phase, it was replaced with PPO.
Improve DeepDip to its final version, v1.
This should be achieved by implementing known improvements to the DQN algorithm such as Dueling Networks, or Prioritized Experience Replay.