As of today, the code does not support R-network training for non-DMLab scenarios. You can use provided checkpoints instead.

google-research / episodic-curiosity

Tensorflow/Keras code and trained models for Episodic Curiosity Through Reachability

Apache License 2.0

199 stars 34 forks source link

As of today, the code does not support R-network training for non-DMLab scenarios. You can use provided checkpoints instead. #13

Open Jingjinganhao opened 3 years ago

Jingjinganhao commented 3 years ago

Hi, I want to train R-network for ant_no_reward env, but when I run python -m launcher_script --workdir=/tmp/ec_workdir --method=ppo_plus_ec --scenario=ant_no_reward it shows As of today, the code does not support R-network training for non-DMLab scenarios. You can use provided checkpoints instead. How can I fix it?

o00000o commented 3 years ago

hi,May I ask how you solved problem RuntimeError: Failed to connect RL API ? Could you help me