The following problem occurred when “updata_policy” was carried out, hope to get help, thank you #13
Description
if trajectory_steps >= self.trajectory_length: # trajectory_length:5
self.agent.reset_lstm_hidden_state(done=False)
trajectory_steps = 0
if step > self.warmup:
self.update_policy()
...
--> 295 if maxlen > 0 and maxlen + 1 < T :
296 t = random.randrange(T - maxlen - 1) # Include next state after final "maxlen" state
297 return mem[t:t + maxlen + 1]
TypeError: '>' not supported between instances of 'NoneType' and 'int'