03:58:10 evaluator INFO:duckietown-challenges:duckietown-challenges 3.2.12
03:58:11 evaluator INFO:duckietown-challenges:evaluation: Preparing here..
03:58:11 evaluator INFO:duckietown-challenges:evaluation: Solution parameters: OrderedDict([('env', 'Duckietown-Lf-Lfv-Navv-Silent-v1')])
03:58:11 evaluator DEBUG:duckietown-challenges:evaluation: gym started with pid = 90
03:58:11 evaluator INFO:duckietown-challenges:evaluation: Waiting for Gym to activate...
03:58:11 evaluator INFO:duckietown-challenges:evaluation: Preparation done.
03:58:11 evaluator DEBUG:duckietown-challenges:Written to: /challenge-description/description.yaml
03:58:11 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (0 secs passed, will wait 600 secs more)
03:58:11 evaluator launch.sh >  Starting xvfb
03:58:11 evaluator launch.sh >  Started xvfb with PID 92
03:58:11 evaluator launch.sh >  Now running gym_simulation_launcher.py
03:58:11 evaluator INFO:duckietown-challenges:duckietown-challenges 3.2.12
03:58:11 evaluator INFO:duckietown-slimremote:duckietown-slimremote 2018.10.1
03:58:11 evaluator INFO:gym-duckietown:gym-duckietown 2018.10.1
03:58:11 evaluator 
03:58:12 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_obstacles-v0
03:58:12 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-straight_road-v0
03:58:12 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-zigzag_dists-v0
03:58:12 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_dyn_duckiebots-v0
03:58:12 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_pedestrians-v0
03:58:12 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-test_loop_obstacles-v0
03:58:12 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-udem1-v0
03:58:12 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_empty-v0
03:58:12 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-4way-v0
03:58:12 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-small_loop-v0
03:58:12 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-small_loop_cw-v0
03:58:12 evaluator WARNING:rosout:Failed to load Python extension for LZ4 support. LZ4 compression will not be available.
03:58:12 evaluator        launcher|gym_simulation_launcher.py:48   - main           | launcher parameters:
03:58:12 evaluator 
03:58:12 evaluator {
03:58:12 evaluator     "challenge": "LF", 
03:58:12 evaluator     "episodes": 5, 
03:58:12 evaluator     "steps_per_episode": 500, 
03:58:12 evaluator     "environment-constructor": "Simulator", 
03:58:12 evaluator     "include_map": true, 
03:58:12 evaluator     "environment-parameters": {
03:58:12 evaluator         "seed": 123, 
03:58:12 evaluator         "map_name": "loop_pedestrians", 
03:58:12 evaluator         "max_steps": 500000, 
03:58:12 evaluator         "domain_rand": 0, 
03:58:12 evaluator         "camera_width": 640, 
03:58:12 evaluator         "camera_height": 480, 
03:58:12 evaluator         "accept_start_angle_deg": 4, 
03:58:12 evaluator         "full_transparency": true, 
03:58:12 evaluator         "distortion": true
03:58:12 evaluator     }, 
03:58:12 evaluator     "agent-info": {
03:58:12 evaluator         "challenge": "LF"
03:58:12 evaluator     }
03:58:12 evaluator }
03:58:12 evaluator        launcher|gym_simulation_launcher.py:59   - main           | using gym-duckietown version 2018.10.1
03:58:12 evaluator  gym-duckietown|    graphics.py:121  - create_frame_buffers| Falling back to non-multisampled frame buffer
03:58:12 evaluator  gym-duckietown|    graphics.py:121  - create_frame_buffers| Falling back to non-multisampled frame buffer
03:58:12 evaluator  gym-duckietown|   simulator.py:490  - _load_map      | loading map file "/workspace/gym-duckietown/gym_duckietown/maps/loop_pedestrians.yaml"
03:58:12 evaluator  gym-duckietown|     objmesh.py:50   - __init__       | loading mesh "/workspace/gym-duckietown/gym_duckietown/meshes/duckiebot.obj"
03:58:12 evaluator  gym-duckietown|     objmesh.py:238  - _load_mtl      | loading materials from "/workspace/gym-duckietown/gym_duckietown/meshes/duckiebot.mtl"
03:58:13 evaluator  gym-duckietown|     objmesh.py:50   - __init__       | loading mesh "/workspace/gym-duckietown/gym_duckietown/meshes/duckie.obj"
03:58:13 evaluator  gym-duckietown|    graphics.py:60   - load_texture   | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/duckie.png"
03:58:13 evaluator  gym-duckietown|     objmesh.py:50   - __init__       | loading mesh "/workspace/gym-duckietown/gym_duckietown/meshes/cone.obj"
03:58:13 evaluator  gym-duckietown|    graphics.py:60   - load_texture   | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/cone.png"
03:58:13 evaluator  gym-duckietown|     objmesh.py:50   - __init__       | loading mesh "/workspace/gym-duckietown/gym_duckietown/meshes/barrier.obj"
03:58:13 evaluator  gym-duckietown|    graphics.py:60   - load_texture   | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/barrier.png"
03:58:13 evaluator  gym-duckietown|    graphics.py:60   - load_texture   | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/floor_1.png"
03:58:13 evaluator  gym-duckietown|    graphics.py:60   - load_texture   | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/curve_left_1.png"
03:58:13 evaluator  gym-duckietown|    graphics.py:60   - load_texture   | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/straight_1.png"
03:58:13 evaluator  gym-duckietown|    graphics.py:60   - load_texture   | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/curve_right_1.png"
03:58:13 evaluator  gym-duckietown|   simulator.py:471  - reset          | Starting at [4.05833625 0.         2.17835003] 1.62929007381
03:58:17 evaluator        launcher|gym_simulation_launcher.py:74   - main           | Logging gym state to: /tmp/tmpXRPWZd/episodes
03:58:17 evaluator  gym-duckietown|   simulator.py:471  - reset          | Starting at [2.75442323 0.         3.0079666 ] 4.83604950287
03:58:17 evaluator        launcher|gym_simulation_launcher.py:89   - main           | Simulator listening to incoming connections...
03:58:17 evaluator        launcher|gym_simulation_launcher.py:98   - main           | Starting episode ep000
03:58:17 evaluator        launcher|gym_simulation_launcher.py:104  - main           | Logging basic info
03:58:17 evaluator        launcher|gym_simulation_launcher.py:109  - main           | Now running episode
03:58:17 evaluator  gym-duckietown|   simulator.py:471  - reset          | Starting at [3.57449761 0.         1.00806868] 0.0328325810557
03:58:17 evaluator        launcher|gym_simulation_launcher.py:237  - run_episode    | received ping: {u'topic': 1, u'ip': u'172.19.0.2', u'id': u'85313', u'msg': u'0'}
03:58:17 evaluator        launcher|gym_simulation_launcher.py:240  - run_episode    | received 2, resetting: {u'topic': 2, u'ip': u'172.19.0.2', u'id': u'85313', u'msg': u'0'}
03:58:17 evaluator  gym-duckietown|   simulator.py:471  - reset          | Starting at [3.9473256  0.         2.19364627] 4.70207132071
03:58:18 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=24, reward=-0.633, done=False
03:58:19 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=48, reward=-0.627, done=False
03:58:20 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=72, reward=-1.523, done=False
03:58:21 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=96, reward=-1.879, done=False
03:58:21 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (10 secs passed, will wait 590 secs more)
03:58:22 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=120, reward=-2.541, done=False
03:58:23 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=144, reward=-3.369, done=False
03:58:24 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=168, reward=-4.291, done=False
03:58:24 evaluator  gym-duckietown|   simulator.py:1244 - step           | Stopping the simulator because we are at an invalid pose.
03:58:24 evaluator        launcher|gym_simulation_launcher.py:116  - main           | Finished episode ep000
03:58:24 evaluator        launcher|gym_simulation_launcher.py:119  - main           | 169 steps are enough
03:58:24 evaluator        launcher|gym_simulation_launcher.py:98   - main           | Starting episode ep001
03:58:24 evaluator        launcher|gym_simulation_launcher.py:104  - main           | Logging basic info
03:58:24 evaluator        launcher|gym_simulation_launcher.py:109  - main           | Now running episode
03:58:24 evaluator  gym-duckietown|   simulator.py:471  - reset          | Starting at [3.76064694 0.         1.32780327] 4.70968603566
03:58:29 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=24, reward=-0.418, done=False
03:58:30 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=48, reward=-0.402, done=False
03:58:31 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (20 secs passed, will wait 580 secs more)
03:58:31 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=72, reward=-0.394, done=False
03:58:32 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=96, reward=-0.402, done=False
03:58:33 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=120, reward=-0.398, done=False
03:58:34 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=144, reward=-0.42, done=False
03:58:34 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=168, reward=-0.442, done=False
03:58:35 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=192, reward=-0.458, done=False
03:58:36 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=216, reward=-0.479, done=False
03:58:38 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=240, reward=-1.302, done=False
03:58:39 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=264, reward=-0.668, done=False
03:58:40 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=288, reward=-0.699, done=False
03:58:41 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=312, reward=-1.755, done=False
03:58:41 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (30 secs passed, will wait 570 secs more)
03:58:41 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=336, reward=-2.861, done=False
03:58:42 evaluator  gym-duckietown|   simulator.py:1244 - step           | Stopping the simulator because we are at an invalid pose.
03:58:42 evaluator        launcher|gym_simulation_launcher.py:116  - main           | Finished episode ep001
03:58:42 evaluator        launcher|gym_simulation_launcher.py:119  - main           | 356 steps are enough
03:58:42 evaluator        launcher|gym_simulation_launcher.py:98   - main           | Starting episode ep002
03:58:42 evaluator        launcher|gym_simulation_launcher.py:104  - main           | Logging basic info
03:58:42 evaluator        launcher|gym_simulation_launcher.py:109  - main           | Now running episode
03:58:42 evaluator  gym-duckietown|   simulator.py:471  - reset          | Starting at [1.19991874 0.         1.04887923] 3.10261496322
03:58:47 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=24, reward=-1.989, done=False
03:58:48 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=48, reward=-1.394, done=False
03:58:49 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=72, reward=-0.394, done=False
03:58:50 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=96, reward=-0.534, done=False
03:58:50 evaluator  gym-duckietown|   simulator.py:1244 - step           | Stopping the simulator because we are at an invalid pose.
03:58:50 evaluator        launcher|gym_simulation_launcher.py:116  - main           | Finished episode ep002
03:58:50 evaluator        launcher|gym_simulation_launcher.py:119  - main           | 113 steps are enough
03:58:50 evaluator        launcher|gym_simulation_launcher.py:98   - main           | Starting episode ep003
03:58:50 evaluator        launcher|gym_simulation_launcher.py:104  - main           | Logging basic info
03:58:50 evaluator        launcher|gym_simulation_launcher.py:109  - main           | Now running episode
03:58:50 evaluator  gym-duckietown|   simulator.py:471  - reset          | Starting at [2.65733059 0.         2.53968888] 3.71783871533
03:58:51 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (40 secs passed, will wait 560 secs more)
03:58:55 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=24, reward=-1.851, done=False
03:58:56 evaluator  gym-duckietown|   simulator.py:1244 - step           | Stopping the simulator because we are at an invalid pose.
03:58:56 evaluator        launcher|gym_simulation_launcher.py:116  - main           | Finished episode ep003
03:58:56 evaluator        launcher|gym_simulation_launcher.py:119  - main           | 41 steps are enough
03:58:56 evaluator        launcher|gym_simulation_launcher.py:98   - main           | Starting episode ep004
03:58:56 evaluator        launcher|gym_simulation_launcher.py:104  - main           | Logging basic info
03:58:56 evaluator        launcher|gym_simulation_launcher.py:109  - main           | Now running episode
03:58:56 evaluator  gym-duckietown|   simulator.py:471  - reset          | Starting at [3.73122222 0.         0.98704716] 3.03336507754
03:59:01 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=24, reward=-1.447, done=False
03:59:01 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (50 secs passed, will wait 550 secs more)
03:59:02 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=48, reward=-1.361, done=False
03:59:02 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=72, reward=-1.282, done=False
03:59:03 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=96, reward=-1.176, done=False
03:59:04 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=120, reward=-1.069, done=False
03:59:05 03:58:09 solution INFO:gym-duckietown-agent:gym-duckietown-agent 2018.10.1
03:58:09 solution INFO:duckietown-challenges:duckietown-challenges 3.2.13
03:58:10 solution DEBUG:duckietown-challenges:Output /challenge-description/description.yaml not ready yet (0 secs passed, will wait 600 secs more)
03:58:12 solution INFO:duckietown-challenges:solution:Parameters: OrderedDict([('env', 'Duckietown-Lf-Lfv-Navv-Silent-v1')])
03:58:12 solution INFO:duckietown-challenges:solution:Starting.
03:58:12 solution INFO:duckietown-challenges:solution:Creating model.
03:58:12 solution INFO:duckietown-challenges:solution:Making environment
03:58:12 solution INFO:duckietown-slimremote:duckietown-slimremote 2018.10.1
03:58:12 solution INFO:duckietown-challenges:solution:Reset environment
03:58:15 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again
03:58:27 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again
03:58:45 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again
03:58:53 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again
03:58:59 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again
03:59:20 solution INFO:duckietown-challenges:solution:Finished.
03:59:20 solution DEBUG:duckietown-challenges:Written to: /challenge-solution-output/output-solution.yaml
03:59:21 solution INFO:duckietown-challenges:solution:Graceful termination of wrap_solution().
03:59:21 solution Starting submission
03:59:21 solution (u'starting sub socket on', 8902)
evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=144, reward=-0.964, done=False
03:59:06 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=168, reward=-0.826, done=False
03:59:07 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=192, reward=-0.715, done=False
03:59:08 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=216, reward=-0.632, done=False
03:59:10 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=240, reward=-0.528, done=False
03:59:11 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=264, reward=-0.428, done=False
03:59:11 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (60 secs passed, will wait 540 secs more)
03:59:12 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=288, reward=-0.314, done=False
03:59:13 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=312, reward=-1.046, done=False
03:59:14 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=336, reward=-4.332, done=False
03:59:15 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=360, reward=-4.8, done=False
03:59:16 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=384, reward=-1.885, done=False
03:59:16 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=408, reward=0.185, done=False
03:59:17 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=432, reward=0.317, done=False
03:59:18 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=456, reward=0.36, done=False
03:59:19 evaluator        launcher|gym_simulation_launcher.py:231  - run_episode    | step_count=480, reward=0.23, done=False
03:59:20 evaluator        launcher|gym_simulation_launcher.py:255  - run_episode    | breaking because steps = 500
03:59:20 evaluator        launcher|gym_simulation_launcher.py:116  - main           | Finished episode ep004
03:59:20 evaluator        launcher|gym_simulation_launcher.py:119  - main           | 500 steps are enough
03:59:20 evaluator        launcher|gym_simulation_launcher.py:140  - main           | Simulation done.
03:59:20 evaluator        launcher|gym_simulation_launcher.py:152  - main           | Clean exit.
03:59:20 evaluator        launcher|gym_simulation_launcher.py:263  - <module>       | success
03:59:20 evaluator starting pub socket on port 8902
03:59:20 evaluator launch.sh >  gym_simulation_launcher terminated with return code 0
03:59:20 evaluator launch.sh >  Killing xvfb...
03:59:20 evaluator launch.sh >  Killed.
03:59:20 evaluator launch.sh >  Graceful exit of launch.sh with return code 0
03:59:21 evaluator INFO:duckietown-challenges:evaluation: waiting for gym to finish
03:59:21 evaluator INFO:duckietown-challenges:evaluation: finished with return code 0
03:59:21 evaluator INFO:duckietown-challenges:evaluation: saving files
03:59:21 evaluator INFO:duckietown-challenges:evaluation: score() terminated gracefully.
03:59:21 evaluator DEBUG:duckietown-challenges:Written to: /challenge-results/challenge_results.yaml