15:35:51 evaluator INFO:duckietown-challenges:duckietown-challenges 3.2.12 15:35:51 evaluator INFO:duckietown-challenges:evaluation: Preparing here.. 15:35:51 evaluator INFO:duckietown-challenges:evaluation: Solution parameters: OrderedDict([('env', 'Duckietown-Lf-Lfv-Navv-Silent-v1')]) 15:35:51 evaluator DEBUG:duckietown-challenges:evaluation: gym started with pid = 25 15:35:51 evaluator INFO:duckietown-challenges:evaluation: Waiting for Gym to activate... 15:35:51 evaluator INFO:duckietown-challenges:evaluation: Preparation done. 15:35:51 evaluator DEBUG:duckietown-challenges:Written to: /challenge-description/description.yaml 15:35:51 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (0 secs passed, will wait 600 secs more) 15:35:51 evaluator launch.sh > Starting xvfb 15:35:51 evaluator launch.sh > Started xvfb with PID 27 15:35:51 evaluator launch.sh > Now running gym_simulation_launcher.py 15:35:52 evaluator INFO:duckietown-challenges:duckietown-challenges 3.2.12 15:35:52 evaluator INFO:duckietown-slimremote:duckietown-slimremote 2018.10.1 15:35:52 evaluator INFO:gym-duckietown:gym-duckietown 2018.10.1 15:35:52 evaluator 15:35:52 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-straight_road-v0 15:35:52 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-zigzag_dists-v0 15:35:52 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_pedestrians-v0 15:35:52 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-test_loop_obstacles-v0 15:35:52 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_empty-v0 15:35:52 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_dyn_duckiebots-v0 15:35:52 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-udem1-v0 15:35:52 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-small_loop_cw-v0 15:35:52 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-4way-v0 15:35:52 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-small_loop-v0 15:35:52 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_obstacles-v0 15:35:52 evaluator WARNING:rosout:Failed to load Python extension for LZ4 support. LZ4 compression will not be available. 15:35:52 evaluator launcher|gym_simulation_launcher.py:48 - main | launcher parameters: 15:35:52 evaluator 15:35:52 evaluator { 15:35:52 evaluator "challenge": "LF", 15:35:52 evaluator "episodes": 5, 15:35:52 evaluator "steps_per_episode": 500, 15:35:52 evaluator "environment-constructor": "Simulator", 15:35:52 evaluator "include_map": true, 15:35:52 evaluator "environment-parameters": { 15:35:52 evaluator "seed": 123, 15:35:52 evaluator "map_name": "loop_empty", 15:35:52 evaluator "max_steps": 500001, 15:35:52 evaluator "domain_rand": 0, 15:35:52 evaluator "camera_width": 640, 15:35:52 evaluator "camera_height": 480, 15:35:52 evaluator "accept_start_angle_deg": 4, 15:35:52 evaluator "full_transparency": true, 15:35:52 evaluator "distortion": true 15:35:52 evaluator }, 15:35:52 evaluator "agent-info": { 15:35:52 evaluator "challenge": "LF" 15:35:52 evaluator } 15:35:52 evaluator } 15:35:52 evaluator launcher|gym_simulation_launcher.py:59 - main | using gym-duckietown version 2018.10.1 15:35:52 evaluator gym-duckietown| graphics.py:121 - create_frame_buffers| Falling back to non-multisampled frame buffer 15:35:52 evaluator gym-duckietown| graphics.py:121 - create_frame_buffers| Falling back to non-multisampled frame buffer 15:35:52 evaluator gym-duckietown| simulator.py:490 - _load_map | loading map file "/workspace/gym-duckietown/gym_duckietown/maps/loop_empty.yaml" 15:35:52 evaluator gym-duckietown| objmesh.py:50 - __init__ | loading mesh "/workspace/gym-duckietown/gym_duckietown/meshes/duckiebot.obj" 15:35:52 evaluator gym-duckietown| objmesh.py:238 - _load_mtl | loading materials from "/workspace/gym-duckietown/gym_duckietown/meshes/duckiebot.mtl" 15:35:53 evaluator gym-duckietown| objmesh.py:50 - __init__ | loading mesh "/workspace/gym-duckietown/gym_duckietown/meshes/duckie.obj" 15:35:53 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/duckie.png" 15:35:53 evaluator gym-duckietown| objmesh.py:50 - __init__ | loading mesh "/workspace/gym-duckietown/gym_duckietown/meshes/cone.obj" 15:35:53 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/cone.png" 15:35:53 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/floor_1.png" 15:35:53 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/curve_left_1.png" 15:35:53 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/straight_1.png" 15:35:53 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/curve_right_1.png" 15:35:53 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [4.05833625 0. 2.17835003] 1.62929007381 15:35:56 evaluator launcher|gym_simulation_launcher.py:74 - main | Logging gym state to: /tmp/tmp29jq82/episodes 15:35:56 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [2.75442323 0. 3.0079666 ] 4.83604950287 15:35:56 evaluator launcher|gym_simulation_launcher.py:89 - main | Simulator listening to incoming connections... 15:35:56 evaluator launcher|gym_simulation_launcher.py:98 - main | Starting episode ep000 15:35:56 evaluator launcher|gym_simulation_launcher.py:104 - main | Logging basic info 15:35:56 evaluator launcher|gym_simulation_launcher.py:109 - main | Now running episode 15:35:56 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [3.57449761 0. 1.00806868] 0.0328325810557 15:35:56 evaluator launcher|gym_simulation_launcher.py:237 - run_episode | received ping: {u'topic': 1, u'ip': u'172.18.0.2', u'id': u'70834', u'msg': u'0'} 15:35:56 evaluator launcher|gym_simulation_launcher.py:240 - run_episode | received 2, resetting: {u'topic': 2, u'ip': u'172.18.0.2', u'id': u'70834', u'msg': u'0'} 15:35:56 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [3.9473256 0. 2.19364627] 4.70207132071 15:36:01 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (10 secs passed, will wait 590 secs more) 15:36:02 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=24, reward=-0.63, done=False 15:36:03 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=48, reward=-0.599, done=False 15:36:04 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=72, reward=-1.377, done=False 15:36:06 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=96, reward=-1.519, done=False 15:36:08 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=120, reward=-1.887, done=False 15:36:09 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=144, reward=-2.447, done=False 15:36:10 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=168, reward=-3.131, done=False 15:36:11 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=192, reward=-3.893, done=False 15:36:11 evaluator gym-duckietown| simulator.py:1244 - step | Stopping the simulator because we are at an invalid pose. 15:36:11 evaluator launcher|gym_simulation_launcher.py:116 - main | Finished episode ep000 15:36:11 evaluator launcher|gym_simulation_launcher.py:119 - main | 204 steps are enough 15:36:11 evaluator launcher|gym_simulation_launcher.py:98 - main | Starting episode ep001 15:36:11 evaluator launcher|gym_simulation_launcher.py:104 - main | Logging basic info 15:36:11 evaluator launcher|gym_simulation_launcher.py:109 - main | Now running episode 15:36:11 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (20 secs passed, will wait 580 secs more) 15:36:11 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [3.94220351 0. 1.23114947] 4.68721314392 15:36:16 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=24, reward=-0.56, done=False 15:36:17 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=48, reward=-0.516, done=False 15:36:18 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=72, reward=-0.464, done=False 15:36:19 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=96, reward=-0.41, done=False 15:36:20 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=120, reward=-0.356, done=False 15:36:21 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (30 secs passed, will wait 570 secs more) 15:36:22 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=144, reward=-0.307, done=False 15:36:23 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=168, reward=-0.262, done=False 15:36:24 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=192, reward=-0.223, done=False 15:36:25 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=216, reward=-0.189, done=False 15:36:26 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=240, reward=-0.159, done=False 15:36:27 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=264, reward=-0.131, done=False 15:36:28 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=288, reward=-0.102, done=False 15:36:29 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=312, reward=-0.879, done=False 15:36:30 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=336, reward=-0.969, done=False 15:36:31 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=360, reward=-1.323, done=False 15:36:31 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (40 secs passed, will wait 560 secs more) 15:36:32 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=384, reward=-1.903, done=False 15:36:33 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=408, reward=-2.618, done=False 15:36:34 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=432, reward=-3.407, done=False 15:36:35 evaluator gym-duckietown| simulator.py:1244 - step | Stopping the simulator because we are at an invalid pose. 15:36:35 evaluator launcher|gym_simulation_launcher.py:116 - main | Finished episode ep001 15:36:35 evaluator launcher|gym_simulation_launcher.py:119 - main | 452 steps are enough 15:36:35 evaluator launcher|gym_simulation_launcher.py:98 - main | Starting episode ep002 15:36:35 evaluator launcher|gym_simulation_launcher.py:104 - main | Logging basic info 15:36:35 evaluator launcher|gym_simulation_launcher.py:109 - main | Now running episode 15:36:35 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [0.84497723 0. 1.12248482] 4.62469817798 15:36:40 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=24, reward=-0.038, done=False 15:36:41 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=48, reward=0.051, done=False 15:36:41 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (50 secs passed, will wait 550 secs more) 15:36:42 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=72, reward=0.149, done=False 15:36:43 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=96, reward=0.255, done=False 15:36:44 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=120, reward=0.365, done=False 15:36:45 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=144, reward=0.314, done=False 15:36:46 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=168, reward=0.2, done=False 15:36:48 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=192, reward=0.087, done=False 15:36:49 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=216, reward=-0.03, done=False 15:36:50 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=240, reward=-0.153, done=False 15:36:51 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=264, reward=-0.286, done=False 15:36:51 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (60 secs passed, will wait 540 secs more) 15:36:52 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=288, reward=-0.429, done=False 15:36:53 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=312, reward=-0.581, done=False 15:36:54 evaluator gym-duckietown| simulator.py:1244 - step | Stopping the simulator because we are at an invalid pose. 15:36:54 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=336, reward=-1000, done=True 15:36:54 evaluator launcher|gym_simulation_launcher.py:116 - main | Finished episode ep002 15:36:54 evaluator launcher|gym_simulation_launcher.py:119 - main | 336 steps are enough 15:36:54 evaluator launcher|gym_simulation_launcher.py:98 - main | Starting episode ep003 15:36:54 evaluator launcher|gym_simulation_launcher.py:104 - main | Logging basic info 15:36:54 evaluator launcher|gym_simulation_launcher.py:109 - main | Now running episode 15:36:54 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [3.00329777 0. 0.86708317] 0.0349480490083 15:36:59 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=24, reward=-1.331, done=False 15:37:00 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=48, reward=-1.36, done=False 15:37:01 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=72, reward=-1.389, done=False 15:37:01 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (70 secs passed, will wait 530 secs more) 15:37:02 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=96, reward=-1.416, done=False 15:37:03 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=120, reward=-1.442, done=False 15:37:04 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=144, reward=-1.467, done=False 15:37:05 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=168, reward=-1.49, done=False 15:37:06 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=192, reward=-2.382, done=False 15:37:07 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=216, reward=-2.641, done=False 15:37:08 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=240, reward=-3.063, done=False 15:37:09 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=264, reward=-3.623, done=False 15:37:10 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=288, reward=-4.282, done=False 15:37:11 evaluator gym-duckietown| simulator.py:1244 - step | Stopping the simulator because we are at an invalid pose. 15:37:11 evaluator launcher|gym_simulation_launcher.py:116 - main | Finished episode ep003 15:37:11 evaluator launcher|gym_simulation_launcher.py:119 - main | 310 steps are enough 15:37:11 evaluator launcher|gym_simulation_launcher.py:98 - main | Starting episode ep004 15:37:11 evaluator launcher|gym_simulation_launcher.py:104 - main | Logging basic info 15:37:11 evaluator launcher|gym_simulation_launcher.py:109 - main | Now running episode 15:37:11 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [1.72410152 0. 3.21929481] 0.0317184229532 15:37:11 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (80 secs passed, will wait 520 secs more) 15:37:16 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=24, reward=-2.205, done=False 15:37:17 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=48, reward=-2.229, done=False 15:37:18 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=72, reward=-2.251, done=False 15:37:19 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=96, reward=-2.271, done=False 15:37:20 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=120, reward=-2.289, done=False 15:37:21 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=144, reward=-2.308, done=False 15:37:21 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (90 secs passed, will wait 510 secs more) 15:37:22 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | 15:35:52 solution INFO:gym-duckietown-agent:gym-duckietown-agent 2018.10.1 15:35:52 solution INFO:duckietown-challenges:duckietown-challenges 3.2.14 15:35:53 solution INFO:duckietown-challenges:solution:Parameters: OrderedDict([('env', 'Duckietown-Lf-Lfv-Navv-Silent-v1')]) 15:35:53 solution INFO:duckietown-challenges:solution:Starting. 15:35:53 solution INFO:duckietown-challenges:solution:Creating model. 15:35:53 solution INFO:duckietown-challenges:solution:Making environment 15:35:53 solution INFO:duckietown-slimremote:duckietown-slimremote 2018.10.1 15:35:53 solution INFO:duckietown-challenges:solution:Reset environment 15:35:53 solution 2018-11-07 15:35:53.594232: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 15:35:53 solution 2018-11-07 15:35:53.604140: E tensorflow/stream_executor/cuda/cuda_driver.cc:300] failed call to cuInit: UNKNOWN ERROR (-1) 15:35:53 solution 2018-11-07 15:35:53.604899: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:157] no NVIDIA GPU device is present: /dev/nvidia0 does not exist 15:35:56 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again 15:36:00 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again 15:36:14 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again 15:36:38 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again 15:36:57 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again 15:37:14 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again 15:37:28 solution INFO:duckietown-challenges:solution:Finished. 15:37:28 solution DEBUG:duckietown-challenges:Written to: /challenge-solution-output/output-solution.yaml 15:37:29 solution INFO:duckietown-challenges:solution:Graceful termination of wrap_solution(). 15:37:29 solution Starting submission 15:37:29 solution (u'starting sub socket on', 8902) 15:37:29 solution prefix/x 15:37:29 solution prefix/ConvNet/Reshape/shape 15:37:29 solution prefix/ConvNet/Reshape 15:37:29 solution prefix/ConvNet/conv_layer_1/kernel 15:37:29 solution prefix/ConvNet/conv_layer_1/kernel/read 15:37:29 solution prefix/ConvNet/conv_layer_1/bias 15:37:29 solution prefix/ConvNet/conv_layer_1/bias/read 15:37:29 solution prefix/ConvNet/conv_layer_1/Conv2D 15:37:29 solution prefix/ConvNet/conv_layer_1/BiasAdd 15:37:29 solution prefix/ConvNet/conv_layer_1/Relu 15:37:29 solution prefix/ConvNet/max_pooling2d/MaxPool 15:37:29 solution prefix/ConvNet/conv_layer_2/kernel 15:37:29 solution prefix/ConvNet/conv_layer_2/kernel/read 15:37:29 solution prefix/ConvNet/conv_layer_2/bias 15:37:29 solution prefix/ConvNet/conv_layer_2/bias/read 15:37:29 solution prefix/ConvNet/conv_layer_2/Conv2D 15:37:29 solution prefix/ConvNet/conv_layer_2/BiasAdd 15:37:29 solution prefix/ConvNet/conv_layer_2/Relu 15:37:29 solution prefix/ConvNet/max_pooling2d_1/MaxPool 15:37:29 solution prefix/ConvNet/flatten/Shape 15:37:29 solution prefix/ConvNet/flatten/strided_slice/stack 15:37:29 solution prefix/ConvNet/flatten/strided_slice/stack_1 15:37:29 solution prefix/ConvNet/flatten/strided_slice/stack_2 15:37:29 solution prefix/ConvNet/flatten/strided_slice 15:37:29 solution prefix/ConvNet/flatten/Reshape/shape/1 15:37:29 solution prefix/ConvNet/flatten/Reshape/shape 15:37:29 solution prefix/ConvNet/flatten/Reshape 15:37:29 solution prefix/ConvNet/fc_layer_1/kernel 15:37:29 solution prefix/ConvNet/fc_layer_1/kernel/read 15:37:29 solution prefix/ConvNet/fc_layer_1/bias 15:37:29 solution prefix/ConvNet/fc_layer_1/bias/read 15:37:29 solution prefix/ConvNet/fc_layer_1/MatMul 15:37:29 solution prefix/ConvNet/fc_layer_1/BiasAdd 15:37:29 solution prefix/ConvNet/fc_layer_1/Relu 15:37:29 solution prefix/ConvNet/fc_layer_2/kernel 15:37:29 solution prefix/ConvNet/fc_layer_2/kernel/read 15:37:29 solution prefix/ConvNet/fc_layer_2/bias 15:37:29 solution prefix/ConvNet/fc_layer_2/bias/read 15:37:29 solution prefix/ConvNet/fc_layer_2/MatMul 15:37:29 solution prefix/ConvNet/fc_layer_2/BiasAdd [32mstep_count=168, reward=-2.323, done=False 15:37:23 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=192, reward=-2.329, done=False 15:37:24 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=216, reward=-2.227, done=False 15:37:25 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=240, reward=-1.782, done=False 15:37:26 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=264, reward=-0.916, done=False 15:37:27 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=288, reward=-0.04, done=False 15:37:28 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=312, reward=-0.739, done=False 15:37:28 evaluator gym-duckietown| simulator.py:1244 - step | Stopping the simulator because we are at an invalid pose. 15:37:28 evaluator launcher|gym_simulation_launcher.py:116 - main | Finished episode ep004 15:37:28 evaluator launcher|gym_simulation_launcher.py:119 - main | 325 steps are enough 15:37:28 evaluator starting pub socket on port 8902 15:37:28 evaluator launcher|gym_simulation_launcher.py:140 - main | Simulation done. 15:37:28 evaluator launcher|gym_simulation_launcher.py:152 - main | Clean exit. 15:37:28 evaluator launcher|gym_simulation_launcher.py:263 - <module> | success 15:37:28 evaluator INFO:duckietown-challenges:evaluation: waiting for gym to finish 15:37:29 evaluator launch.sh > gym_simulation_launcher terminated with return code 0 15:37:29 evaluator launch.sh > Killing xvfb... 15:37:29 evaluator launch.sh > Killed. 15:37:29 evaluator launch.sh > Graceful exit of launch.sh with return code 0 15:37:29 evaluator INFO:duckietown-challenges:evaluation: finished with return code 0 15:37:29 evaluator INFO:duckietown-challenges:evaluation: saving files 15:37:29 evaluator INFO:duckietown-challenges:evaluation: score() terminated gracefully. 15:37:29 evaluator DEBUG:duckietown-challenges:Written to: /challenge-results/challenge_results.yaml