qfettes / curiositydrivenexplorationbyselfsupervisedprediction Goto Github PK

Hi, I am trying to train the code, but it appeared this issue.

Traceback (most recent call last):
File "a2c_devel.py", line 381, in
train(config)
File "a2c_devel.py", line 299, in train
last_reward_logged = tb_plot_from_monitor(writer, log_dir, np.mean(config.adaptive_repeat), last_reward_logged, 'episode length')
File "D:\ICM\utils\plot.py", line 420, in tb_plot_from_monitor
x, y = load_raw_eplength_data(log_dir, 1, 1) #load data
File "D:\ICM\utils\plot.py", line 395, in load_raw_eplength_data
t_time = float(tmp[2])
IndexError: list index out of range

Could you tell me how to fix this problem? Thanks

Hi,
your code can run but it would have an error when debugging as follows:
'UnicodeDecodeError: 'utf-8' codec can't decode bytes in position 1022-1023: unexpected end of data.'

 And in the 'ICM_A2C.py', the loss only consists of forward loss and inverse loss like this:   'total_forward_loss + total_inverse_loss'. However,  the loss defined in the paper including other loss.

 Could you give me some advice. Thank you for your reply.