Collaborative Deep Reinforcement Learning

Collaborative Deep Reinforcement Learning (CDRL) is collaborative framework to enable knowledge transfer among heterogeneous tasks.

How to run:

|>heterogeneousTransfer
python train.py --num-MTL-workers 8 0 --env-id PongDeterministic-v3_Bowling-v0

|>CDRL
python train.py --num-MTL-workers 8 8 --env-id PongDeterministic-v3_Bowling-v0

###Acknowledgement
This code refer to OpenAI universe starter agent.