Meet an ValueError when I replace RingNetwork with HighwayNetwork for network in the tutorial03

[17150934]

In the tutorial03, I replace RingNetwork with HighwayNetwork for network ,but I meet an ValueError:

Traceback (most recent call last):
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/tune/trial_runner.py", line 426, in _process_trial
    result = self.trial_executor.fetch_result(trial)
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/tune/ray_trial_executor.py", line 378, in fetch_result
    result = ray.get(trial_future[0], DEFAULT_GET_TIMEOUT)
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/worker.py", line 1457, in get
    raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(ValueError): ray::PPO.train() (pid=10954, ip=192.168.6.112)
  File "python/ray/_raylet.pyx", line 636, in ray._raylet.execute_task
  File "python/ray/_raylet.pyx", line 619, in ray._raylet.execute_task.function_executor
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/agents/trainer.py", line 444, in train
    raise e
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/agents/trainer.py", line 433, in train
    result = Trainable.train(self)
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/tune/trainable.py", line 176, in train
    result = self._train()
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/agents/trainer_template.py", line 129, in _train
    fetches = self.optimizer.step()
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/optimizers/multi_gpu_optimizer.py", line 140, in step
    self.num_envs_per_worker, self.train_batch_size)
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/optimizers/rollout.py", line 29, in collect_samples
    next_sample = ray_get_and_free(fut_sample)
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/utils/memory.py", line 33, in ray_get_and_free
    result = ray.get(object_ids)
ray.exceptions.RayTaskError(ValueError): ray::RolloutWorker.sample() (pid=11030, ip=192.168.6.112)
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/utils/tf_run_builder.py", line 94, in run_timeline
    fetches = sess.run(ops, feed_dict=feed_dict)
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 956, in run
    run_metadata_ptr)
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1156, in _run
    (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (1, 42) for Tensor 'default_policy/observation:0', which has shape '(?, 44)'

During handling of the above exception, another exception occurred:

ray::RolloutWorker.sample() (pid=11030, ip=192.168.6.112)
  File "python/ray/_raylet.pyx", line 633, in ray._raylet.execute_task
  File "python/ray/_raylet.pyx", line 634, in ray._raylet.execute_task
  File "python/ray/_raylet.pyx", line 636, in ray._raylet.execute_task
  File "python/ray/_raylet.pyx", line 619, in ray._raylet.execute_task.function_executor
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/evaluation/rollout_worker.py", line 471, in sample
    batches = [self.input_reader.next()]
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/evaluation/sampler.py", line 56, in next
    batches = [self.get_data()]
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/evaluation/sampler.py", line 99, in get_data
    item = next(self.rollout_provider)
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/evaluation/sampler.py", line 327, in _env_runner
    active_episodes)
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/evaluation/sampler.py", line 551, in _do_policy_eval
    eval_results[k] = builder.get(v)
  File "/home/vcdc/anaconda3/envs/flow/lib/python3.7/site-packages/ray/rllib/utils/tf_run_builder.py", line 53, in get
    self.fetches, self.feed_dict))
ValueError: Error fetching: [<tf.Tensor 'default_policy/add:0' shape=(?, 1) dtype=float32>, {'action_prob': <tf.Tensor 'default_policy/Exp_1:0' shape=(?,) dtype=float32>, 'action_logp': <tf.Tensor 'default_policy/sub_2:0' shape=(?,) dtype=float32>, 'vf_preds': <tf.Tensor 'default_policy/Reshape:0' shape=(?,) dtype=float32>, 'behaviour_logits': <tf.Tensor 'default_policy/model/fc_out/BiasAdd:0' shape=(?, 2) dtype=float32>}], feed_dict={<tf.Tensor 'default_policy/observation:0' shape=(?, 44) dtype=float32>: [array([0.44409109, 0.44405716, 0.44405939, 0.44408473, 0.44404423,
       0.44407543, 0.44402707, 0.44407156, 0.44409773, 0.44407641,
       0.44411795, 0.44408998, 0.4440337 , 0.44362106, 0.44408406,
       0.44404458, 0.44409067, 0.3988301 , 0.44532913, 0.44532913,
       0.01731031, 0.09245801, 0.09184036, 0.09243479, 0.09184368,
       0.27578934, 0.27271432, 0.27350743, 0.27468785, 0.45574352,
       0.45488228, 0.45227   , 0.45656885, 0.63957073, 0.63730218,
       0.63756669, 0.63982425, 0.81881247, 0.81595532, 0.81928188,
       0.81876308, 0.91137627])], <tf.Tensor 'default_policy/action:0' shape=(?, 1) dtype=float32>: [array([0.7231164], dtype=float32)], <tf.Tensor 'default_policy/prev_reward:0' shape=(?,) dtype=float32>: [0.41458751306631525], <tf.Tensor 'default_policy/PlaceholderWithDefault:0' shape=() dtype=bool>: False}

When I set the horizon to a low value(eg. 110),It is correct,but it produce the error above when I set the horizon to a high value(eg.200) Why?

[TrinhTuanHung2021]

I also got this error and I see no one currently supports the use of this tool. This team hasn't commented for almost a year now