Jaeseok Kim

Results 6 issues of Jaeseok Kim

Hi, I am modifying the program for my project. When I see the code, muupan used only one network to solve the problem. However, if you use one network, the...

aal@aal-ThinkPad-S5-S540:~/Downloads/dqn-in-the-caffe-master$ ./dqn -gui A.L.E: Arcade Learning Environment (version 0.5.1) [Powered by Stella] Use -help for help screen. Game console created: ROM file: breakout.bin Cart Name: Breakout - Breakaway IV (1978)...

error: RuntimeError: output with shape [1, 28, 28] doesn't match the broadcast shape [3, 28, 28] MNIST has [1, 28, 28] and [3. 28. 28] two format. In this code,...

Dear qiexing, Thank you for sharing your work. During the training, you can use file txt, which is **caffe-regression/kaggle_fkp_data/train_data_list.txt** Can you share the list file? Also, did you develop the...

I0801 19:47:21.416074 21668 solver.cpp:398] Test net output #0: accuracy = 1 I0801 19:47:21.416137 21668 solver.cpp:398] Test net output #1: accuracy = 0 I0801 19:47:21.416157 21668 solver.cpp:398] Test net output #2:...

Thank you for sharing this code. When I run this code, I got the error In DQNAgentWithHER.py, Line 106 q_pred = self.q_eval.forward(concat_state_goal)[batches, action] IndexError: tensors used as indices must be...