poca-SoccerTwos / run_logs /timers.json
caiAtSNU's picture
First Push
489ffbf
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.932747483253479,
"min": 1.9121804237365723,
"max": 1.932747483253479,
"count": 4
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 61847.91796875,
"min": 61189.7734375,
"max": 61847.91796875,
"count": 4
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 998.0,
"max": 999.0,
"count": 4
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 31968.0,
"min": 31936.0,
"max": 31968.0,
"count": 4
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 7
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 7
},
"SoccerTwos.Step.mean": {
"value": 5059342.0,
"min": 5009348.0,
"max": 5059342.0,
"count": 6
},
"SoccerTwos.Step.sum": {
"value": 5059342.0,
"min": 5009348.0,
"max": 5059342.0,
"count": 6
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 3.11944677378051e-06,
"min": 1.211162299341595e-07,
"max": 8.596443876740523e-06,
"count": 6
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 3.11944677378051e-05,
"min": 1.2111622709198855e-06,
"max": 8.596444240538403e-05,
"count": 6
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.5998024309737957e-06,
"min": -5.9235476328467485e-06,
"max": 6.031579687260091e-06,
"count": 6
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 1.5998024537111633e-05,
"min": -5.9235477237962186e-05,
"max": 6.031579687260091e-05,
"count": 6
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 6
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 6
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 6
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 6
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 6
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 6
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.016910106994004713,
"min": 0.016910106994004713,
"max": 0.016910106994004713,
"count": 1
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.016910106994004713,
"min": 0.016910106994004713,
"max": 0.016910106994004713,
"count": 1
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 5.203159360157707e-10,
"min": 5.203159360157707e-10,
"max": 5.203159360157707e-10,
"count": 1
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 5.203159360157707e-10,
"min": 5.203159360157707e-10,
"max": 5.203159360157707e-10,
"count": 1
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 1.0902630872185645e-09,
"min": 1.0902630872185645e-09,
"max": 1.0902630872185645e-09,
"count": 1
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 1.0902630872185645e-09,
"min": 1.0902630872185645e-09,
"max": 1.0902630872185645e-09,
"count": 1
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 1
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 1
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.19999999999999993,
"min": 0.19999999999999993,
"max": 0.19999999999999993,
"count": 1
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.19999999999999993,
"min": 0.19999999999999993,
"max": 0.19999999999999993,
"count": 1
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 1
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 1
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1691883628",
"python_version": "3.9.17 (main, Jul 5 2023, 20:41:20) \n[GCC 11.2.0]",
"command_line_arguments": "/home/caiprozect/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
"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": "1691883871"
},
"total": 242.91582610000023,
"count": 1,
"self": 0.004804800000329124,
"children": {
"run_training.setup": {
"total": 0.01344810000000507,
"count": 1,
"self": 0.01344810000000507
},
"TrainerController.start_learning": {
"total": 242.8975731999999,
"count": 1,
"self": 0.127469100016242,
"children": {
"TrainerController._reset_env": {
"total": 5.0458490999994865,
"count": 2,
"self": 5.0458490999994865
},
"TrainerController.advance": {
"total": 237.38003809998418,
"count": 4003,
"self": 0.13206499996158527,
"children": {
"env_step": {
"total": 176.54905049999888,
"count": 4003,
"self": 105.27152680002791,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.20696579998139,
"count": 4003,
"self": 1.18824589998394,
"children": {
"TorchPolicy.evaluate": {
"total": 70.01871989999745,
"count": 8000,
"self": 70.01871989999745
}
}
},
"workers": {
"total": 0.07055789998958062,
"count": 4003,
"self": 0.0,
"children": {
"worker_root": {
"total": 213.47908389999338,
"count": 4003,
"is_parallel": true,
"self": 121.48394169999756,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0028379999998833227,
"count": 2,
"is_parallel": true,
"self": 0.001293400000577094,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015445999993062287,
"count": 8,
"is_parallel": true,
"self": 0.0015445999993062287
}
}
},
"UnityEnvironment.step": {
"total": 0.031495900000209076,
"count": 1,
"is_parallel": true,
"self": 0.00044709999974656967,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003415000001041335,
"count": 1,
"is_parallel": true,
"self": 0.0003415000001041335
},
"communicator.exchange": {
"total": 0.029106200000114768,
"count": 1,
"is_parallel": true,
"self": 0.029106200000114768
},
"steps_from_proto": {
"total": 0.0016011000002436049,
"count": 2,
"is_parallel": true,
"self": 0.00029520000043703476,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013058999998065701,
"count": 8,
"is_parallel": true,
"self": 0.0013058999998065701
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.0013414000004559057,
"count": 2,
"is_parallel": true,
"self": 0.0002929000006588467,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001048499999797059,
"count": 8,
"is_parallel": true,
"self": 0.001048499999797059
}
}
},
"UnityEnvironment.step": {
"total": 91.99380079999537,
"count": 4002,
"is_parallel": true,
"self": 2.838800399992124,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.0368807000068045,
"count": 4002,
"is_parallel": true,
"self": 2.0368807000068045
},
"communicator.exchange": {
"total": 78.37068119999549,
"count": 4002,
"is_parallel": true,
"self": 78.37068119999549
},
"steps_from_proto": {
"total": 8.747438500000953,
"count": 8004,
"is_parallel": true,
"self": 1.9054108999730488,
"children": {
"_process_rank_one_or_two_observation": {
"total": 6.8420276000279046,
"count": 32016,
"is_parallel": true,
"self": 6.8420276000279046
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 60.69892260002371,
"count": 4003,
"self": 0.609781000019666,
"children": {
"process_trajectory": {
"total": 9.842308100004175,
"count": 4003,
"self": 9.42228290000412,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4200252000000546,
"count": 1,
"self": 0.4200252000000546
}
}
},
"_update_policy": {
"total": 50.246833499999866,
"count": 2,
"self": 9.924011200002042,
"children": {
"TorchPOCAOptimizer.update": {
"total": 40.322822299997824,
"count": 83,
"self": 40.322822299997824
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.100000190490391e-06,
"count": 1,
"self": 1.100000190490391e-06
},
"TrainerController._save_models": {
"total": 0.3442157999998017,
"count": 1,
"self": 0.0028419999998732237,
"children": {
"RLTrainer._checkpoint": {
"total": 0.34137379999992845,
"count": 1,
"self": 0.34137379999992845
}
}
}
}
}
}
}