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