09:56:49 evaluator INFO:duckietown-challenges:duckietown-challenges 3.2.12 09:56:50 evaluator INFO:duckietown-challenges:evaluation: Preparing here.. 09:56:50 evaluator INFO:duckietown-challenges:evaluation: Solution parameters: OrderedDict([('env', 'Duckietown-Lf-Lfv-Navv-Silent-v1')]) 09:56:50 evaluator DEBUG:duckietown-challenges:evaluation: gym started with pid = 90 09:56:50 evaluator INFO:duckietown-challenges:evaluation: Waiting for Gym to activate... 09:56:50 evaluator INFO:duckietown-challenges:evaluation: Preparation done. 09:56:50 evaluator DEBUG:duckietown-challenges:Written to: /challenge-description/description.yaml 09:56:50 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (0 secs passed, will wait 600 secs more) 09:56:50 evaluator launch.sh > Starting xvfb 09:56:50 evaluator launch.sh > Started xvfb with PID 92 09:56:50 evaluator launch.sh > Now running gym_simulation_launcher.py 09:56:50 evaluator INFO:duckietown-challenges:duckietown-challenges 3.2.12 09:56:51 evaluator INFO:duckietown-slimremote:duckietown-slimremote 2018.10.1 09:56:51 evaluator INFO:gym-duckietown:gym-duckietown 2018.10.1 09:56:51 evaluator 09:56:51 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_obstacles-v0 09:56:51 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-straight_road-v0 09:56:51 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-zigzag_dists-v0 09:56:51 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_dyn_duckiebots-v0 09:56:51 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_pedestrians-v0 09:56:51 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-test_loop_obstacles-v0 09:56:51 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-udem1-v0 09:56:51 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-loop_empty-v0 09:56:51 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-4way-v0 09:56:51 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-small_loop-v0 09:56:51 evaluator INFO:gym-duckietown:Registering gym environment id: Duckietown-small_loop_cw-v0 09:56:51 evaluator WARNING:rosout:Failed to load Python extension for LZ4 support. LZ4 compression will not be available. 09:56:51 evaluator launcher|gym_simulation_launcher.py:48 - main | launcher parameters: 09:56:51 evaluator 09:56:51 evaluator { 09:56:51 evaluator "challenge": "LF", 09:56:51 evaluator "episodes": 5, 09:56:51 evaluator "steps_per_episode": 500, 09:56:51 evaluator "environment-constructor": "Simulator", 09:56:51 evaluator "include_map": true, 09:56:51 evaluator "environment-parameters": { 09:56:51 evaluator "seed": 123, 09:56:51 evaluator "map_name": "loop_empty", 09:56:51 evaluator "max_steps": 500001, 09:56:51 evaluator "domain_rand": 0, 09:56:51 evaluator "camera_width": 640, 09:56:51 evaluator "camera_height": 480, 09:56:51 evaluator "accept_start_angle_deg": 4, 09:56:51 evaluator "full_transparency": true, 09:56:51 evaluator "distortion": true 09:56:51 evaluator }, 09:56:51 evaluator "agent-info": { 09:56:51 evaluator "challenge": "LF" 09:56:51 evaluator } 09:56:51 evaluator } 09:56:51 evaluator launcher|gym_simulation_launcher.py:59 - main | using gym-duckietown version 2018.10.1 09:56:51 evaluator gym-duckietown| graphics.py:121 - create_frame_buffers| Falling back to non-multisampled frame buffer 09:56:51 evaluator gym-duckietown| graphics.py:121 - create_frame_buffers| Falling back to non-multisampled frame buffer 09:56:51 evaluator gym-duckietown| simulator.py:490 - _load_map | loading map file "/workspace/gym-duckietown/gym_duckietown/maps/loop_empty.yaml" 09:56:51 evaluator gym-duckietown| objmesh.py:50 - __init__ | loading mesh "/workspace/gym-duckietown/gym_duckietown/meshes/duckiebot.obj" 09:56:51 evaluator gym-duckietown| objmesh.py:238 - _load_mtl | loading materials from "/workspace/gym-duckietown/gym_duckietown/meshes/duckiebot.mtl" 09:56:51 evaluator gym-duckietown| objmesh.py:50 - __init__ | loading mesh "/workspace/gym-duckietown/gym_duckietown/meshes/duckie.obj" 09:56:52 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/duckie.png" 09:56:52 evaluator gym-duckietown| objmesh.py:50 - __init__ | loading mesh "/workspace/gym-duckietown/gym_duckietown/meshes/cone.obj" 09:56:52 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/cone.png" 09:56:52 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/floor_1.png" 09:56:52 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/curve_left_1.png" 09:56:52 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/straight_1.png" 09:56:52 evaluator gym-duckietown| graphics.py:60 - load_texture | loading texture "/workspace/gym-duckietown/gym_duckietown/textures/curve_right_1.png" 09:56:52 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [4.05833625 0. 2.17835003] 1.62929007381 09:56:55 evaluator launcher|gym_simulation_launcher.py:74 - main | Logging gym state to: /tmp/tmpOzP_0J/episodes 09:56:55 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [2.75442323 0. 3.0079666 ] 4.83604950287 09:56:56 evaluator launcher|gym_simulation_launcher.py:89 - main | Simulator listening to incoming connections... 09:56:56 evaluator launcher|gym_simulation_launcher.py:98 - main | Starting episode ep000 09:56:56 evaluator launcher|gym_simulation_launcher.py:104 - main | Logging basic info 09:56:56 evaluator launcher|gym_simulation_launcher.py:109 - main | Now running episode 09:56:56 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [3.57449761 0. 1.00806868] 0.0328325810557 09:56:56 evaluator launcher|gym_simulation_launcher.py:237 - run_episode | received ping: {u'topic': 1, u'ip': u'172.31.0.2', u'id': u'1353', u'msg': u'0'} 09:56:56 evaluator launcher|gym_simulation_launcher.py:240 - run_episode | received 2, resetting: {u'topic': 2, u'ip': u'172.31.0.2', u'id': u'1353', u'msg': u'0'} 09:56:56 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [3.9473256 0. 2.19364627] 4.70207132071 09:57:00 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (10 secs passed, will wait 590 secs more) 09:57:00 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=24, reward=-0.629, done=False 09:57:01 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=48, reward=-0.599, done=False 09:57:02 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=72, reward=-1.463, done=False 09:57:03 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=96, reward=-1.837, done=False 09:57:04 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=120, reward=-2.474, done=False 09:57:05 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=144, reward=-3.338, done=False 09:57:05 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=168, reward=-4.294, done=False 09:57:05 evaluator gym-duckietown| simulator.py:1244 - step | Stopping the simulator because we are at an invalid pose. 09:57:05 evaluator launcher|gym_simulation_launcher.py:116 - main | Finished episode ep000 09:57:05 evaluator launcher|gym_simulation_launcher.py:119 - main | 169 steps are enough 09:57:05 evaluator launcher|gym_simulation_launcher.py:98 - main | Starting episode ep001 09:57:05 evaluator launcher|gym_simulation_launcher.py:104 - main | Logging basic info 09:57:05 evaluator launcher|gym_simulation_launcher.py:109 - main | Now running episode 09:57:05 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [3.94220351 0. 1.23114947] 4.68721314392 09:57:10 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (20 secs passed, will wait 580 secs more) 09:57:10 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=24, reward=-0.562, done=False 09:57:11 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=48, reward=-0.526, done=False 09:57:12 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=72, reward=-0.511, done=False 09:57:13 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=96, reward=-0.496, done=False 09:57:14 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=120, reward=-0.467, done=False 09:57:15 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=144, reward=-0.436, done=False 09:57:15 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=168, reward=-0.423, done=False 09:57:16 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=192, reward=-0.419, done=False 09:57:17 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=216, reward=-0.421, done=False 09:57:18 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=240, reward=-0.42, done=False 09:57:19 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=264, reward=-1.218, done=False 09:57:20 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (30 secs passed, will wait 570 secs more) 09:57:20 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=288, reward=-1.413, done=False 09:57:21 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=312, reward=-1.935, done=False 09:57:22 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=336, reward=-2.701, done=False 09:57:22 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=360, reward=-3.6, done=False 09:57:23 evaluator gym-duckietown| simulator.py:1244 - step | Stopping the simulator because we are at an invalid pose. 09:57:23 evaluator launcher|gym_simulation_launcher.py:116 - main | Finished episode ep001 09:57:23 evaluator launcher|gym_simulation_launcher.py:119 - main | 376 steps are enough 09:57:23 evaluator launcher|gym_simulation_launcher.py:98 - main | Starting episode ep002 09:57:23 evaluator launcher|gym_simulation_launcher.py:104 - main | Logging basic info 09:57:23 evaluator launcher|gym_simulation_launcher.py:109 - main | Now running episode 09:57:23 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [0.84497723 0. 1.12248482] 4.62469817798 09:57:28 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=24, reward=-0.019, done=False 09:57:29 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=48, reward=0.073, done=False 09:57:30 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=72, reward=0.156, done=False 09:57:30 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (40 secs passed, will wait 560 secs more) 09:57:31 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=96, reward=0.188, done=False 09:57:32 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=120, reward=0.227, done=False 09:57:33 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=144, reward=0.275, done=False 09:57:33 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=168, reward=0.322, done=False 09:57:34 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=192, reward=0.394, done=False 09:57:35 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=216, reward=0.313, done=False 09:57:36 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=240, reward=0.243, done=False 09:57:37 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=264, reward=0.204, done=False 09:57:38 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=288, reward=0.177, done=False 09:57:39 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=312, reward=0.162, done=False 09:57:40 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=336, reward=0.176, done=False 09:57:40 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (50 secs passed, will wait 550 secs more) 09:57:40 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=360, reward=0.162, done=False 09:57:41 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=384, reward=0.115, done=False 09:57:42 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=408, reward=0.063, done=False 09:57:43 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=432, reward=-0.054, done=False 09:57:44 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=456, reward=-0.361, done=False 09:57:45 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=480, reward=-0.874, done=False 09:57:46 evaluator launcher|gym_simulation_launcher.py:255 - run_episode | breaking because steps = 500 09:57:46 evaluator launcher|gym_simulation_launcher.py:116 - main | Finished episode ep002 09:57:46 evaluator launcher|gym_simulation_launcher.py:119 - main | 500 steps are enough 09:57:46 evaluator launcher|gym_simulation_launcher.py:98 - main | Starting episode ep003 09:57:46 evaluator launcher|gym_simulation_launcher.py:104 - main | Logging basic info 09:57:46 evaluator launcher|gym_simulation_launcher.py:109 - main | Now running episode 09:57:46 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [3.00329777 0. 0.86708317] 0.0349480490083 09:57:47 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=24, reward=-1.351, done=False 09:57:47 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=48, reward=-1.381, done=False 09:57:49 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=72, reward=-1.416, done=False 09:57:49 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=96, reward=-1.448, done=False 09:57:50 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (60 secs passed, will wait 540 secs more) 09:57:50 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=120, reward=-1.46, done=False 09:57:51 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=144, reward=-2.243, done=False 09:57:52 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=168, reward=-2.356, done=False 09:57:53 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=192, reward=-2.71, done=False 09:57:54 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=216, reward=-3.302, done=False 09:57:55 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=240, reward=-4.07, done=False 09:57:55 evaluator gym-duckietown| simulator.py:1244 - step | Stopping the simulator because we are at an invalid pose. 09:57:55 evaluator launcher|gym_simulation_launcher.py:116 - main | Finished episode ep003 09:57:55 evaluator launcher|gym_simulation_launcher.py:119 - main | 258 steps are enough 09:57:55 evaluator launcher|gym_simulation_launcher.py:98 - main | Starting episode ep004 09:57:55 evaluator launcher|gym_simulation_launcher.py:104 - main | Logging basic info 09:57:55 evaluator launcher|gym_simulation_launcher.py:109 - main | Now running episode 09:57:55 evaluator gym-duckietown| simulator.py:471 - reset | Starting at [1.72410152 0. 3.21929481] 0.0317184229532 09:58:00 evaluator DEBUG:duckietown-challenges:Output /challenge-solution-output/output-solution.yaml not ready yet (70 secs passed, will wait 530 secs more) 09:58:00 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=24, reward=-2.214, done=False 09:58:01 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=48, reward=-2.226, done=False 09:58:02 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=72, reward=-2.209, done=False 09:58:03 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=96, reward=-2.207, done=False 09:58:03 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=120, reward=-2.222, done=False 09:58:04 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=144, reward=-2.255, done=False 09:58:05 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=168, reward=-2.299, done=False 09:58:06 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=192, reward=-2.144, done=False 09:58:07 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=216, reward=-1.175, done=False 09:58:08 evaluator launcher|09:56:49 solution INFO:gym-duckietown-agent:gym-duckietown-agent 2018.10.1 09:56:49 solution INFO:duckietown-challenges:duckietown-challenges 3.2.13 09:56:50 solution DEBUG:duckietown-challenges:Output /challenge-description/description.yaml not ready yet (0 secs passed, will wait 600 secs more) 09:56:51 solution INFO:duckietown-challenges:solution:Parameters: OrderedDict([('env', 'Duckietown-Lf-Lfv-Navv-Silent-v1')]) 09:56:51 solution INFO:duckietown-challenges:solution:Starting. 09:56:51 solution INFO:duckietown-challenges:solution:Creating model. 09:56:51 solution INFO:duckietown-challenges:solution:Making environment 09:56:51 solution INFO:duckietown-slimremote:duckietown-slimremote 2018.10.1 09:56:51 solution INFO:duckietown-challenges:solution:Reset environment 09:56:54 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again 09:56:58 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again 09:57:08 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again 09:57:26 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again 09:57:58 solution INFO:duckietown-slimremote:Simulator not ready - wait 1 second and try again 09:58:09 solution INFO:duckietown-challenges:solution:Finished. 09:58:09 solution DEBUG:duckietown-challenges:Written to: /challenge-solution-output/output-solution.yaml 09:58:10 solution INFO:duckietown-challenges:solution:Graceful termination of wrap_solution(). 09:58:10 solution Starting submission 09:58:10 solution (u'starting sub socket on', 8902) gym_simulation_launcher.py:231 - run_episode | step_count=240, reward=-0.14, done=False 09:58:09 evaluator launcher|gym_simulation_launcher.py:231 - run_episode | step_count=264, reward=-0.738, done=False 09:58:09 evaluator gym-duckietown| simulator.py:1244 - step | Stopping the simulator because we are at an invalid pose. 09:58:09 evaluator launcher|gym_simulation_launcher.py:116 - main | Finished episode ep004 09:58:09 evaluator launcher|gym_simulation_launcher.py:119 - main | 274 steps are enough 09:58:09 evaluator launcher|gym_simulation_launcher.py:140 - main | Simulation done. 09:58:09 evaluator launcher|gym_simulation_launcher.py:152 - main | Clean exit. 09:58:09 evaluator launcher|gym_simulation_launcher.py:263 - <module> | success 09:58:09 evaluator starting pub socket on port 8902 09:58:09 evaluator launch.sh > gym_simulation_launcher terminated with return code 0 09:58:09 evaluator launch.sh > Killing xvfb... 09:58:09 evaluator launch.sh > Killed. 09:58:09 evaluator launch.sh > Graceful exit of launch.sh with return code 0 09:58:10 evaluator INFO:duckietown-challenges:evaluation: waiting for gym to finish 09:58:10 evaluator INFO:duckietown-challenges:evaluation: finished with return code 0 09:58:10 evaluator INFO:duckietown-challenges:evaluation: saving files 09:58:10 evaluator INFO:duckietown-challenges:evaluation: score() terminated gracefully. 09:58:10 evaluator DEBUG:duckietown-challenges:Written to: /challenge-results/challenge_results.yaml