SimoMaestri comments

Repositories
Issues
Comments

Results 4 comments of


                                            SimoMaestri

DQN-Social Attention in Highway-env

Hi, thank you so much for this exhaustive and very clear explanation.

Extract SHAP values from TQC, PPO trained model

Hi, thank you for your answer. I've got another question about the notebook. When you define the "explain" function you also define the model: `model = ([ddpg.S], ddpg.a)` Is ddpg.a...

Extract SHAP values from TQC, PPO trained model

Hi, thank you for your answer. I'll share my code because i have some problem and there are some parts that i really don't understand. I've tried to print your...

SHAP with DQN

Hi, i solved the problem in this way: `explainer = shap.DeepExplainer(model.q_net, torch.FloatTensor(state_log).to(device))` I used model = model.q_net that is the network between state and Q-value. Then i convert state_log to...