self.width = width
states, actions, rewards = escape.generate_episodes(
- nb_train_samples + nb_test_samples, height, width, 3 * T
+ nb_train_samples + nb_test_samples, height, width, T
)
seq = escape.episodes2seq(states, actions, rewards, lookahead_delta=T)
- seq = seq[:, seq.size(1) // 3 : 2 * seq.size(1) // 3]
+ # seq = seq[:, seq.size(1) // 3 : 2 * seq.size(1) // 3]
self.train_input = seq[:nb_train_samples].to(self.device)
self.test_input = seq[nb_train_samples:].to(self.device)