osbm's picture
First Push
e7788f6
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.071541666984558,
"min": 1.0637391805648804,
"max": 2.871727705001831,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10290.0146484375,
"min": 10290.0146484375,
"max": 29409.36328125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.941195487976074,
"min": 0.3927670419216156,
"max": 12.97571086883545,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2523.533203125,
"min": 76.19680786132812,
"max": 2647.044921875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.067935570292249,
"min": 0.06060294801109729,
"max": 0.07492823289580616,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.271742281168996,
"min": 0.24241179204438917,
"max": 0.36037947906366113,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2059515878265979,
"min": 0.11355343966644404,
"max": 0.27879054178209867,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8238063513063916,
"min": 0.4542137586657762,
"max": 1.3939527089104933,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.15909090909091,
"min": 3.3863636363636362,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1107.0,
"min": 149.0,
"max": 1397.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.15909090909091,
"min": 3.3863636363636362,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1107.0,
"min": 149.0,
"max": 1397.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1680691261",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1680691713"
},
"total": 452.3474678140001,
"count": 1,
"self": 0.6838713420002023,
"children": {
"run_training.setup": {
"total": 0.1084991599998375,
"count": 1,
"self": 0.1084991599998375
},
"TrainerController.start_learning": {
"total": 451.55509731200004,
"count": 1,
"self": 0.5515358209931946,
"children": {
"TrainerController._reset_env": {
"total": 3.780655354999908,
"count": 1,
"self": 3.780655354999908
},
"TrainerController.advance": {
"total": 446.9936823400069,
"count": 18222,
"self": 0.25949201201683536,
"children": {
"env_step": {
"total": 446.73419032799006,
"count": 18222,
"self": 329.1805684229728,
"children": {
"SubprocessEnvManager._take_step": {
"total": 117.29206250500374,
"count": 18222,
"self": 1.6878864680022616,
"children": {
"TorchPolicy.evaluate": {
"total": 115.60417603700148,
"count": 18222,
"self": 115.60417603700148
}
}
},
"workers": {
"total": 0.26155940001353883,
"count": 18222,
"self": 0.0,
"children": {
"worker_root": {
"total": 450.0889228920048,
"count": 18222,
"is_parallel": true,
"self": 212.20159284301326,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005085831000087637,
"count": 1,
"is_parallel": true,
"self": 0.003640674000052968,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014451570000346692,
"count": 10,
"is_parallel": true,
"self": 0.0014451570000346692
}
}
},
"UnityEnvironment.step": {
"total": 0.034699070999977266,
"count": 1,
"is_parallel": true,
"self": 0.0005597510000825423,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004211309999391233,
"count": 1,
"is_parallel": true,
"self": 0.0004211309999391233
},
"communicator.exchange": {
"total": 0.03195518500001526,
"count": 1,
"is_parallel": true,
"self": 0.03195518500001526
},
"steps_from_proto": {
"total": 0.001763003999940338,
"count": 1,
"is_parallel": true,
"self": 0.000361818999863317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001401185000077021,
"count": 10,
"is_parallel": true,
"self": 0.001401185000077021
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.88733004899154,
"count": 18221,
"is_parallel": true,
"self": 9.561811640015321,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.312942648985654,
"count": 18221,
"is_parallel": true,
"self": 5.312942648985654
},
"communicator.exchange": {
"total": 192.8436320219996,
"count": 18221,
"is_parallel": true,
"self": 192.8436320219996
},
"steps_from_proto": {
"total": 30.168943737990958,
"count": 18221,
"is_parallel": true,
"self": 5.9279852499798835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.240958488011074,
"count": 182210,
"is_parallel": true,
"self": 24.240958488011074
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013080799999443116,
"count": 1,
"self": 0.00013080799999443116,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 443.9930155080708,
"count": 379497,
"is_parallel": true,
"self": 8.978209481127124,
"children": {
"process_trajectory": {
"total": 242.70173609794278,
"count": 379497,
"is_parallel": true,
"self": 240.9963183029431,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7054177949996756,
"count": 4,
"is_parallel": true,
"self": 1.7054177949996756
}
}
},
"_update_policy": {
"total": 192.3130699290009,
"count": 90,
"is_parallel": true,
"self": 71.86467795400131,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.4483919749996,
"count": 4587,
"is_parallel": true,
"self": 120.4483919749996
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22909298800004763,
"count": 1,
"self": 0.0014284930000485474,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22766449499999908,
"count": 1,
"self": 0.22766449499999908
}
}
}
}
}
}
}