|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 3.2852768898010254, |
|
"min": 3.2852768898010254, |
|
"max": 3.295689105987549, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 68544.015625, |
|
"min": 44251.80078125, |
|
"max": 105462.0546875, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 791.1666666666666, |
|
"min": 539.5, |
|
"max": 999.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 18988.0, |
|
"min": 12948.0, |
|
"max": 27680.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1201.3638652710058, |
|
"min": 1201.3638652710058, |
|
"max": 1201.96281630874, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 7208.183191626034, |
|
"min": 4807.85126523496, |
|
"max": 19230.585048751913, |
|
"count": 4 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 49818.0, |
|
"min": 9864.0, |
|
"max": 49818.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 49818.0, |
|
"min": 9864.0, |
|
"max": 49818.0, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": 0.038771118968725204, |
|
"min": 0.026416150853037834, |
|
"max": 0.0398482121527195, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": 0.46525344252586365, |
|
"min": 0.2969847619533539, |
|
"max": 0.5283676981925964, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.033957596868276596, |
|
"min": 0.02646045573055744, |
|
"max": 0.033957596868276596, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 0.40749114751815796, |
|
"min": 0.277004599571228, |
|
"max": 0.5292844176292419, |
|
"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": -0.1474666694800059, |
|
"min": -0.3333333333333333, |
|
"max": 0.3690200001001358, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": -1.7696000337600708, |
|
"min": -4.0, |
|
"max": 7.380400002002716, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": -0.1474666694800059, |
|
"min": -0.3333333333333333, |
|
"max": 0.3690200001001358, |
|
"count": 5 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": -1.7696000337600708, |
|
"min": -4.0, |
|
"max": 7.380400002002716, |
|
"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": 0.01668152923036056, |
|
"min": 0.016059217835491937, |
|
"max": 0.01668152923036056, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.01668152923036056, |
|
"min": 0.016059217835491937, |
|
"max": 0.01668152923036056, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.0028299271323097247, |
|
"min": 0.0028299271323097247, |
|
"max": 0.005018066718346543, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.0028299271323097247, |
|
"min": 0.0028299271323097247, |
|
"max": 0.005018066718346543, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.0028920475975610315, |
|
"min": 0.0028920475975610315, |
|
"max": 0.004854577826336026, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.0028920475975610315, |
|
"min": 0.0028920475975610315, |
|
"max": 0.004854577826336026, |
|
"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": 0.20000000000000004, |
|
"max": 0.20000000000000007, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000004, |
|
"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": "1679174485", |
|
"python_version": "3.9.15 (main, Dec 8 2022, 00:49:16) \n[GCC 12.2.1 20220819 (Red Hat 12.2.1-2)]", |
|
"command_line_arguments": "/home/andylo/.pyenv/versions/ml-agents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executable/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", |
|
"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": "1679174587" |
|
}, |
|
"total": 101.995251913002, |
|
"count": 1, |
|
"self": 0.27638708299491554, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0205243680102285, |
|
"count": 1, |
|
"self": 0.0205243680102285 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 101.69834046199685, |
|
"count": 1, |
|
"self": 0.07220679831516463, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 2.733346941997297, |
|
"count": 1, |
|
"self": 2.733346941997297 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 98.6726864186785, |
|
"count": 3672, |
|
"self": 0.08446112426463515, |
|
"children": { |
|
"env_step": { |
|
"total": 80.45149370598665, |
|
"count": 3672, |
|
"self": 65.8306553598668, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 14.573734082849114, |
|
"count": 3672, |
|
"self": 0.8748790705285501, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 13.698855012320564, |
|
"count": 7304, |
|
"self": 13.698855012320564 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.047104263270739466, |
|
"count": 3672, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 101.21451693247946, |
|
"count": 3672, |
|
"is_parallel": true, |
|
"self": 45.40902267745696, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005347019003238529, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0010501939977984875, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.004296825005440041, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.004296825005440041 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.02396436399430968, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0011969149927608669, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0009570380061632022, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0009570380061632022 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.018317426001885906, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.018317426001885906 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0034929849934997037, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0006377409736160189, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002855244019883685, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002855244019883685 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 55.805494255022495, |
|
"count": 3671, |
|
"is_parallel": true, |
|
"self": 3.965466091656708, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 2.913448881430668, |
|
"count": 3671, |
|
"is_parallel": true, |
|
"self": 2.913448881430668 |
|
}, |
|
"communicator.exchange": { |
|
"total": 38.04064614143863, |
|
"count": 3671, |
|
"is_parallel": true, |
|
"self": 38.04064614143863 |
|
}, |
|
"steps_from_proto": { |
|
"total": 10.88593314049649, |
|
"count": 7342, |
|
"is_parallel": true, |
|
"self": 1.8423524002428167, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 9.043580740253674, |
|
"count": 29368, |
|
"is_parallel": true, |
|
"self": 9.043580740253674 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 18.13673158842721, |
|
"count": 3672, |
|
"self": 0.6424721075891284, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 4.1980584538396215, |
|
"count": 3672, |
|
"self": 4.1980584538396215 |
|
}, |
|
"_update_policy": { |
|
"total": 13.29620102699846, |
|
"count": 2, |
|
"self": 8.65051618196594, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 4.64568484503252, |
|
"count": 66, |
|
"self": 4.64568484503252 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 6.710033630952239e-07, |
|
"count": 1, |
|
"self": 6.710033630952239e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.2200996320025297, |
|
"count": 1, |
|
"self": 0.001511022011982277, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2185886099905474, |
|
"count": 1, |
|
"self": 0.2185886099905474 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |