MiuLab / DDQ

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning

MiuLab/DDQ Issues

Bug: in run.py, using "world_model.predict_mode", but using "predict_model" in file DDQ/src/deep_dialog/usersims/usersim_model.py where world_model class is implemented.
Updated 3 years ago
agent_dqn.py torch.load can't find zip files under checkpoints/DDQAgent
Closed 3 years ago1
what is pre-training dqn model and world model ? initialize Q(s; a; θQ) and M(s; a; θM) via pre-training on human conversational data？
Updated 4 years ago1
Keras model
Updated 5 years ago
Which pytorch version i should choose? we cannot find the trained model to do the test.
Closed 6 years ago2
about kb_helper.py
Closed 6 years ago1
Line 66 path error on draw_learning_curve.py
Closed 6 years ago1
Training with NLG + NLU error
Closed 6 years ago4
When codebase will be available?
Closed 6 years ago3
Model Testing: AttributeError: 'AgentDQN' object has no attribute 'action'
Closed 6 years ago2