def _render(self, mode='human', close=False):
if close:
# Nothing interesting to close
return
outfile = StringIO() if mode == 'ansi' else sys.stdout
inp = "Total length of input instance: %d, step: %d\n" % (self.input_width, self.time)
outfile.write(inp)
x, y, action = self.read_head_position, self.write_head_position, self.last_action
if action is not None:
inp_act, out_act, pred = action
outfile.write("=" * (len(inp) - 1) + "\n")
y_str = "Output Tape : "
target_str = "Targets : "
if action is not None:
pred_str = self.charmap[pred]
x_str = self._render_observation()
for i in range(-2, len(self.target) + 2):
target_str += self._get_str_target(i)
if i < y - 1:
y_str += self._get_str_target(i)
elif i == (y - 1):
if action is not None and out_act == 1:
color = 'green' if pred == self.target[i] else 'red'
y_str += colorize(pred_str, color, highlight=True)
else:
y_str += self._get_str_target(i)
outfile.write(x_str)
outfile.write(y_str + "\n")
outfile.write(target_str + "\n\n")
if action is not None:
outfile.write("Current reward : %.3f\n" % self.last_reward)
outfile.write("Cumulative reward : %.3f\n" % self.episode_total_reward)
move = self.MOVEMENTS[inp_act]
outfile.write("Action : Tuple(move over input: %s,\n" % move)
out_act = out_act == 1
outfile.write(" write to the output tape: %s,\n" % out_act)
outfile.write(" prediction: %s)\n" % pred_str)
else:
outfile.write("\n" * 5)
return outfile
评论列表
文章目录
