Hi @eleurent . thank you so much for the contribution. Please I need to know how you figured out the hyperparameters of DQN in the highway run env. did you use optuna for optimizing the hyperparameter or another framework for hyperparameter optimization because I want to train A2C and PPO on this env but I'm stuck because it has been months and I didn't get the right hyperparameter. I use stable baseline3 for PPO and A2C but it didn't converge then I use the my own implementation of the A2C and PPO but still stuck can you please help me and thank you so much
Hi @eleurent . thank you so much for the contribution. Please I need to know how you figured out the hyperparameters of DQN in the highway run env. did you use optuna for optimizing the hyperparameter or another framework for hyperparameter optimization because I want to train A2C and PPO on this env but I'm stuck because it has been months and I didn't get the right hyperparameter. I use stable baseline3 for PPO and A2C but it didn't converge then I use the my own implementation of the A2C and PPO but still stuck can you please help me and thank you so much