Ankit Kumar
First Push
5d1ae11
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.734003484249115,
"min": 0.6146830916404724,
"max": 2.868138313293457,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7000.19140625,
"min": 5941.689453125,
"max": 29404.154296875,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.036966323852539,
"min": 0.23821555078029633,
"max": 14.050886154174805,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2737.20849609375,
"min": 46.21381759643555,
"max": 2866.380859375,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.04619872337487626,
"min": 0.035300275465609356,
"max": 0.05562673276085661,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.18479489349950504,
"min": 0.15290963122727894,
"max": 0.27104018708875327,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17768584409107765,
"min": 0.10611372289713472,
"max": 0.276020464549462,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7107433763643106,
"min": 0.4244548915885389,
"max": 1.38010232274731,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.3764995412000025e-06,
"min": 1.3764995412000025e-06,
"max": 0.00029837640054119997,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.50599816480001e-06,
"min": 5.50599816480001e-06,
"max": 0.001477032007656,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10045880000000001,
"min": 0.10045880000000001,
"max": 0.19945880000000002,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40183520000000006,
"min": 0.40183520000000006,
"max": 0.992344,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.289412000000004e-05,
"min": 3.289412000000004e-05,
"max": 0.00497299412,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00013157648000000017,
"min": 0.00013157648000000017,
"max": 0.0246179656,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.133333333333333,
"min": 3.0,
"max": 27.836363636363636,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1221.0,
"min": 132.0,
"max": 1531.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.133333333333333,
"min": 3.0,
"max": 27.836363636363636,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1221.0,
"min": 132.0,
"max": 1531.0,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1697626675",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697628606"
},
"total": 1930.654107932,
"count": 1,
"self": 0.381629933999875,
"children": {
"run_training.setup": {
"total": 0.041146762999915154,
"count": 1,
"self": 0.041146762999915154
},
"TrainerController.start_learning": {
"total": 1930.2313312350002,
"count": 1,
"self": 3.3898680130298544,
"children": {
"TrainerController._reset_env": {
"total": 0.7172528490000332,
"count": 1,
"self": 0.7172528490000332
},
"TrainerController.advance": {
"total": 1926.06418408897,
"count": 90937,
"self": 1.5875737980597933,
"children": {
"env_step": {
"total": 1924.4766102909102,
"count": 90937,
"self": 1468.4817784408601,
"children": {
"SubprocessEnvManager._take_step": {
"total": 454.4393810670467,
"count": 90937,
"self": 7.107732536081812,
"children": {
"TorchPolicy.evaluate": {
"total": 447.3316485309649,
"count": 90937,
"self": 447.3316485309649
}
}
},
"workers": {
"total": 1.55545078300338,
"count": 90937,
"self": 0.0,
"children": {
"worker_root": {
"total": 1923.9537965631027,
"count": 90937,
"is_parallel": true,
"self": 776.3636525121385,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004727159000140091,
"count": 1,
"is_parallel": true,
"self": 0.003594310000380574,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001132848999759517,
"count": 10,
"is_parallel": true,
"self": 0.001132848999759517
}
}
},
"UnityEnvironment.step": {
"total": 0.04420192199995654,
"count": 1,
"is_parallel": true,
"self": 0.0005467000000862754,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023382999984278285,
"count": 1,
"is_parallel": true,
"self": 0.00023382999984278285
},
"communicator.exchange": {
"total": 0.04167875300004198,
"count": 1,
"is_parallel": true,
"self": 0.04167875300004198
},
"steps_from_proto": {
"total": 0.0017426389999855019,
"count": 1,
"is_parallel": true,
"self": 0.0004254120003679418,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00131722699961756,
"count": 10,
"is_parallel": true,
"self": 0.00131722699961756
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1147.5901440509642,
"count": 90936,
"is_parallel": true,
"self": 48.29109200881703,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 27.289921783053842,
"count": 90936,
"is_parallel": true,
"self": 27.289921783053842
},
"communicator.exchange": {
"total": 921.6075682481137,
"count": 90936,
"is_parallel": true,
"self": 921.6075682481137
},
"steps_from_proto": {
"total": 150.40156201097966,
"count": 90936,
"is_parallel": true,
"self": 29.358067190893053,
"children": {
"_process_rank_one_or_two_observation": {
"total": 121.04349482008661,
"count": 909360,
"is_parallel": true,
"self": 121.04349482008661
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00027570000020205043,
"count": 1,
"self": 0.00027570000020205043,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1911.2261498505563,
"count": 2320375,
"is_parallel": true,
"self": 41.142332553843744,
"children": {
"process_trajectory": {
"total": 1127.2905629417155,
"count": 2320375,
"is_parallel": true,
"self": 1124.7231795777154,
"children": {
"RLTrainer._checkpoint": {
"total": 2.5673833640000794,
"count": 20,
"is_parallel": true,
"self": 2.5673833640000794
}
}
},
"_update_policy": {
"total": 742.7932543549971,
"count": 454,
"is_parallel": true,
"self": 262.95963818302357,
"children": {
"TorchPPOOptimizer.update": {
"total": 479.8336161719735,
"count": 10893,
"is_parallel": true,
"self": 479.8336161719735
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.05975058400008493,
"count": 1,
"self": 0.00067960900014441,
"children": {
"RLTrainer._checkpoint": {
"total": 0.05907097499994052,
"count": 1,
"self": 0.05907097499994052
}
}
}
}
}
}
}