In [1]:
from ddpg3 import *
%matplotlib inline


[2016-07-23 20:03:33,571] Site environment registry incorrect: Scoreboard did not register all envs: set(['AcrobotContinuous-v0'])

In [2]:
tf.reset_default_graph()

In [3]:
car = ddpg(environment = 'InvertedPendulum-v1', noise_scale= 1.0, ql2 = 0.01)
car.main()


[2016-07-23 20:03:33,617] Making new env: InvertedPendulum-v1
state dim 4
action dim 1
[2016-07-23 20:03:35,979] Action '0.420525530871' is not contained within action space 'Box(1,)'.
result after minibatch no. 0 : mean squared error: 474.612609863
result after minibatch no. 1000 : mean squared error: 187.150527954
---------------------------------------------------------------------------
KeyboardInterrupt                         Traceback (most recent call last)
<ipython-input-3-615d9472b6da> in <module>()
      1 car = ddpg(environment = 'InvertedPendulum-v1', noise_scale= 1.0, ql2 = 0.01)
----> 2 car.main()

/home/frederik/Dokumente/DeepRL/dpg/ddpg3.py in main(self)
    458 
    459         self.initialize_training(self.sess)
--> 460         return self.start_training()
    461 
    462     def plot_replay_memory_2d_state_histogramm(self):

/home/frederik/Dokumente/DeepRL/dpg/ddpg3.py in start_training(self, maxstep, dataname, save)
    164 
    165             # run episode
--> 166             episode_length = self.run_episode(test_run= False, enable_render=False, limit= 10000)
    167 
    168             self.train_lengths.append(episode_length)

/home/frederik/Dokumente/DeepRL/dpg/ddpg3.py in run_episode(self, enable_render, limit, test_run)
    145 
    146                 if (len(self.replay_memory) > self.warmup) and (self.samples_count % (self.batch_size/2) == 0):
--> 147                     self.train_networks()
    148 
    149             state = state_prime

/home/frederik/Dokumente/DeepRL/dpg/ddpg3.py in train_networks(self)
    411 
    412         if self.step % 10 == 0:
--> 413             self.train_writer.add_summary(summary, self.step)
    414 
    415         if self.step % 1000 == 0:

/home/frederik/anaconda2/lib/python2.7/site-packages/tensorflow/python/training/summary_io.pyc in add_summary(self, summary, global_step)
    133     if isinstance(summary, bytes):
    134       summ = summary_pb2.Summary()
--> 135       summ.ParseFromString(summary)
    136       summary = summ
    137     event = event_pb2.Event(wall_time=time.time(), summary=summary)

/home/frederik/anaconda2/lib/python2.7/site-packages/google/protobuf/message.pyc in ParseFromString(self, serialized)
    183     """
    184     self.Clear()
--> 185     self.MergeFromString(serialized)
    186 
    187   def SerializeToString(self):

/home/frederik/anaconda2/lib/python2.7/site-packages/google/protobuf/internal/python_message.pyc in MergeFromString(self, serialized)
   1089     length = len(serialized)
   1090     try:
-> 1091       if self._InternalParse(serialized, 0, length) != length:
   1092         # The only reason _InternalParse would return early is if it
   1093         # encountered an end-group tag.

/home/frederik/anaconda2/lib/python2.7/site-packages/google/protobuf/internal/python_message.pyc in InternalParse(self, buffer, pos, end)
   1125         pos = new_pos
   1126       else:
-> 1127         pos = field_decoder(buffer, new_pos, end, self, field_dict)
   1128         if field_desc:
   1129           self._UpdateOneofState(field_desc)

/home/frederik/anaconda2/lib/python2.7/site-packages/google/protobuf/internal/decoder.pyc in DecodeRepeatedField(buffer, pos, end, message, field_dict)
    610           raise _DecodeError('Truncated message.')
    611         # Read sub-message.
--> 612         if value.add()._InternalParse(buffer, pos, new_pos) != new_pos:
    613           # The only reason _InternalParse would return early is if it
    614           # encountered an end-group tag.

/home/frederik/anaconda2/lib/python2.7/site-packages/google/protobuf/internal/python_message.pyc in InternalParse(self, buffer, pos, end)
   1125         pos = new_pos
   1126       else:
-> 1127         pos = field_decoder(buffer, new_pos, end, self, field_dict)
   1128         if field_desc:
   1129           self._UpdateOneofState(field_desc)

/home/frederik/anaconda2/lib/python2.7/site-packages/google/protobuf/internal/decoder.pyc in DecodeField(buffer, pos, end, message, field_dict)
    631         raise _DecodeError('Truncated message.')
    632       # Read sub-message.
--> 633       if value._InternalParse(buffer, pos, new_pos) != new_pos:
    634         # The only reason _InternalParse would return early is if it encountered
    635         # an end-group tag.

/home/frederik/anaconda2/lib/python2.7/site-packages/google/protobuf/internal/python_message.pyc in InternalParse(self, buffer, pos, end)
   1125         pos = new_pos
   1126       else:
-> 1127         pos = field_decoder(buffer, new_pos, end, self, field_dict)
   1128         if field_desc:
   1129           self._UpdateOneofState(field_desc)

/home/frederik/anaconda2/lib/python2.7/site-packages/google/protobuf/internal/decoder.pyc in DecodePackedField(buffer, pos, end, message, field_dict)
    210         while pos < endpoint:
    211           (element, pos) = decode_value(buffer, pos)
--> 212           value.append(element)
    213         if pos > endpoint:
    214           del value[-1]   # Discard corrupt value.

/home/frederik/anaconda2/lib/python2.7/site-packages/google/protobuf/internal/containers.pyc in append(self, value)
    250     """Appends an item to the list. Similar to list.append()."""
    251     self._values.append(self._type_checker.CheckValue(value))
--> 252     if not self._message_listener.dirty:
    253       self._message_listener.Modified()
    254 

KeyboardInterrupt: 

In [ ]:


In [ ]: