|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 3.2780816555023193, |
|
"min": 3.2780816555023193, |
|
"max": 3.295722246170044, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 56015.859375, |
|
"min": 56015.859375, |
|
"max": 105463.109375, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 605.125, |
|
"min": 587.4, |
|
"max": 905.375, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19364.0, |
|
"min": 11748.0, |
|
"max": 28972.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1196.014512870435, |
|
"min": 1196.014512870435, |
|
"max": 1198.7628881094324, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 11960.145128704351, |
|
"min": 2397.525776218865, |
|
"max": 11960.145128704351, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 49090.0, |
|
"min": 9502.0, |
|
"max": 49090.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 49090.0, |
|
"min": 9502.0, |
|
"max": 49090.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": -0.03394897282123566, |
|
"min": -0.04529840126633644, |
|
"max": -0.023741234093904495, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": -0.5431835651397705, |
|
"min": -0.6341169476509094, |
|
"max": -0.26115357875823975, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.03245082497596741, |
|
"min": -0.04534430801868439, |
|
"max": -0.026336921378970146, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -0.5192131996154785, |
|
"min": -0.6346637606620789, |
|
"max": -0.28970614075660706, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": -0.454925000667572, |
|
"min": -0.5454545454545454, |
|
"max": 0.14209999640782675, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": -7.278800010681152, |
|
"min": -7.278800010681152, |
|
"max": 1.705199956893921, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": -0.454925000667572, |
|
"min": -0.5454545454545454, |
|
"max": 0.14209999640782675, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": -7.278800010681152, |
|
"min": -7.278800010681152, |
|
"max": 1.705199956893921, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.018921801114144425, |
|
"min": 0.01434671591996448, |
|
"max": 0.018921801114144425, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.018921801114144425, |
|
"min": 0.01434671591996448, |
|
"max": 0.018921801114144425, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.002682930588101347, |
|
"min": 0.002682930588101347, |
|
"max": 0.004390325373969972, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.002682930588101347, |
|
"min": 0.002682930588101347, |
|
"max": 0.004390325373969972, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.002740729476014773, |
|
"min": 0.002740729476014773, |
|
"max": 0.004103882494382561, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.002740729476014773, |
|
"min": 0.002740729476014773, |
|
"max": 0.004103882494382561, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 2 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1681934997", |
|
"python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/poca/SoccerTwos.yaml --env /content/SoccerTwos/SoccerTwos.x86_64 --run-id=resnet --no-graphics --force", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1681936173" |
|
}, |
|
"total": 1176.1212460670004, |
|
"count": 1, |
|
"self": 0.5430273430001762, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.07048233500006518, |
|
"count": 1, |
|
"self": 0.07048233500006518 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1175.507736389, |
|
"count": 1, |
|
"self": 0.17357786499587746, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 1.5672324099999742, |
|
"count": 1, |
|
"self": 1.5672324099999742 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1173.4296994920046, |
|
"count": 3550, |
|
"self": 0.21493554701464745, |
|
"children": { |
|
"env_step": { |
|
"total": 1002.921079540996, |
|
"count": 3550, |
|
"self": 978.1015735619897, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 24.715271759999155, |
|
"count": 3550, |
|
"self": 1.1307893260022865, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 23.584482433996868, |
|
"count": 7066, |
|
"self": 23.584482433996868 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.10423421900713947, |
|
"count": 3550, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1172.6111429720002, |
|
"count": 3550, |
|
"is_parallel": true, |
|
"self": 217.11023709299707, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.008438354999952935, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0016366510000125345, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0068017039999404005, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0068017039999404005 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.43893334899996717, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008413420000579208, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0036638550000134273, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0036638550000134273 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.41848312399997667, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.41848312399997667 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.015945027999919148, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.005764648999956989, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.010180378999962159, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.010180378999962159 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 955.5009058790031, |
|
"count": 3549, |
|
"is_parallel": true, |
|
"self": 3.8111998070088475, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 13.415442104990007, |
|
"count": 3549, |
|
"is_parallel": true, |
|
"self": 13.415442104990007 |
|
}, |
|
"communicator.exchange": { |
|
"total": 902.249224545003, |
|
"count": 3549, |
|
"is_parallel": true, |
|
"self": 902.249224545003 |
|
}, |
|
"steps_from_proto": { |
|
"total": 36.025039422001214, |
|
"count": 7098, |
|
"is_parallel": true, |
|
"self": 5.310405344013702, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 30.71463407798751, |
|
"count": 28392, |
|
"is_parallel": true, |
|
"self": 30.71463407798751 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 170.29368440399412, |
|
"count": 3550, |
|
"self": 1.2198223509980153, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 24.33414305499616, |
|
"count": 3550, |
|
"self": 24.33414305499616 |
|
}, |
|
"_update_policy": { |
|
"total": 144.73971899799994, |
|
"count": 2, |
|
"self": 13.03287446399986, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 131.70684453400008, |
|
"count": 60, |
|
"self": 131.70684453400008 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1569995876925532e-06, |
|
"count": 1, |
|
"self": 1.1569995876925532e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.33722546499984674, |
|
"count": 1, |
|
"self": 0.004264644999693701, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.33296082000015303, |
|
"count": 1, |
|
"self": 0.33296082000015303 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |