Implement resume training

laermannjan / nip-deeprl-project

Student project in deep reinforcement learning with the OpenAI Gym. We evaluated and analyzed how different model architectures performed as agents in various games.

0 stars 0 forks source link

Implement resume training #14

Open laermannjan opened 7 years ago

laermannjan commented 7 years ago

When we stop training after a number of steps or episodes and save the logs and models we should be able to resume training the same agent given all these infos (DQNs are certainly capable, why aren't we?)

laermannjan commented 7 years ago

Entrypoint is given in testbench.py via --load-on-start option. Not implemented yet.