BatchNorm is not supported for algorithms other than DDPG

[redknightlois]

Latest code raises the following error. Same code on 12.1 works properly.

Original stack trace for 'main_level/agent/main/online/network_0/behavior/behavior':
  File "C:\Anaconda3\lib\site-packages\rl_coach\graph_managers\graph_manager.py", line 148, in create_graph
    self.level_managers, self.environments = self._create_graph(task_parameters)
  File "C:\Anaconda3\lib\site-packages\rl_coach\graph_managers\basic_rl_graph_manager.py", line 72, in _create_graph
    level_manager = LevelManager(agents=agent, environment=env, name="main_level")
  File "C:\Anaconda3\lib\site-packages\rl_coach\level_manager.py", line 91, in __init__
    self.build(spaces_definition)
  File "C:\Anaconda3\lib\site-packages\rl_coach\level_manager.py", line 165, in build
    [agent.set_environment_parameters(spaces) for agent in self.agents.values()]
  File "C:\Anaconda3\lib\site-packages\rl_coach\level_manager.py", line 165, in <listcomp>
    [agent.set_environment_parameters(spaces) for agent in self.agents.values()]
  File "C:\Anaconda3\lib\site-packages\rl_coach\agents\agent.py", line 335, in set_environment_parameters
    self.init_environment_dependent_modules()
  File "C:\Anaconda3\lib\site-packages\rl_coach\agents\value_optimization_agent.py", line 46, in init_environment_dependent_modules
    super().init_environment_dependent_modules()
  File "C:\Anaconda3\lib\site-packages\rl_coach\agents\agent.py", line 380, in init_environment_dependent_modules
    self.networks = self.create_networks()
  File "C:\Anaconda3\lib\site-packages\rl_coach\agents\agent.py", line 353, in create_networks
    worker_device=self.worker_device)
  File "C:\Anaconda3\lib\site-packages\rl_coach\architectures\network_wrapper.py", line 86, in __init__
    network_is_trainable=True)
  File "C:\Anaconda3\lib\site-packages\rl_coach\architectures\tensorflow_components\general_network.py", line 74, in construct
    return construct_on_device()
  File "C:\Anaconda3\lib\site-packages\rl_coach\architectures\tensorflow_components\general_network.py", line 59, in construct_on_device
    return GeneralTensorFlowNetwork(*args, **kwargs)
  File "C:\Anaconda3\lib\site-packages\rl_coach\architectures\tensorflow_components\general_network.py", line 126, in __init__
    network_is_local, network_is_trainable)
  File "C:\Anaconda3\lib\site-packages\rl_coach\architectures\tensorflow_components\architecture.py", line 105, in __init__
    self.weights = self.get_model()
  File "C:\Anaconda3\lib\site-packages\rl_coach\architectures\tensorflow_components\general_network.py", line 262, in get_model
    input_placeholder, embedding = input_embedder()
  File "C:\Anaconda3\lib\site-packages\rl_coach\architectures\tensorflow_components\embedders\embedder.py", line 86, in __call__
    self.input = tf.placeholder("float", shape=[None] + self.input_size, name=self.get_name())
  File "C:\Anaconda3\lib\site-packages\tensorflow\python\ops\array_ops.py", line 2143, in placeholder
    return gen_array_ops.placeholder(dtype=dtype, shape=shape, name=name)
  File "C:\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 7400, in placeholder
    "Placeholder", dtype=dtype, shape=shape, name=name)
  File "C:\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 788, in _apply_op_helper
    op_def=op_def)
  File "C:\Anaconda3\lib\site-packages\tensorflow\python\util\deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "C:\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3616, in create_op
    op_def=op_def)
  File "C:\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 2005, in __init__
    self._traceback = tf_stack.extract_stack()