cannot evaluate on trained model

muupan / async-rl

Replicating "Asynchronous Methods for Deep Reinforcement Learning" (http://arxiv.org/abs/1602.01783)

MIT License

400 stars 81 forks source link

cannot evaluate on trained model #27

Open goodnamegood opened 7 years ago

goodnamegood commented 7 years ago

I trained the model for 3000000 iterations and saved the model as "3000000.h5". But when I try to evaluate using demo_a3c_ale.py, it turns out there is an error there saying "Value Error (inconsistent group is specified)" at line 61: serializers.load_hdf5(args.model, model).