Cornelias's picture
First commit
6d82ba3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8546156883239746,
"min": 0.8546156883239746,
"max": 2.8539817333221436,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8122.267578125,
"min": 8122.267578125,
"max": 29133.4453125,
"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": 13.107945442199707,
"min": 0.3686201870441437,
"max": 13.107945442199707,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2556.04931640625,
"min": 71.51231384277344,
"max": 2655.6845703125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06747444827273927,
"min": 0.062082213261187555,
"max": 0.07143694421170307,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26989779309095707,
"min": 0.2610867865048075,
"max": 0.35718472105851534,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19959512688949993,
"min": 0.11883285817320405,
"max": 0.27929996111813715,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7983805075579997,
"min": 0.4753314326928162,
"max": 1.3964998055906857,
"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.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.90909090909091,
"min": 3.522727272727273,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1140.0,
"min": 155.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.90909090909091,
"min": 3.522727272727273,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1140.0,
"min": 155.0,
"max": 1429.0,
"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": "1749062006",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749062420"
},
"total": 414.1342990150001,
"count": 1,
"self": 0.4359882830001425,
"children": {
"run_training.setup": {
"total": 0.023202611999977307,
"count": 1,
"self": 0.023202611999977307
},
"TrainerController.start_learning": {
"total": 413.67510812,
"count": 1,
"self": 0.31391495998059327,
"children": {
"TrainerController._reset_env": {
"total": 3.9891646999999466,
"count": 1,
"self": 3.9891646999999466
},
"TrainerController.advance": {
"total": 409.27129266501925,
"count": 18192,
"self": 0.3383665970225138,
"children": {
"env_step": {
"total": 288.4614615429939,
"count": 18192,
"self": 219.31603440698723,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.95472542500056,
"count": 18192,
"self": 1.2090597650246764,
"children": {
"TorchPolicy.evaluate": {
"total": 67.74566565997588,
"count": 18192,
"self": 67.74566565997588
}
}
},
"workers": {
"total": 0.19070171100611333,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 412.3189904939918,
"count": 18192,
"is_parallel": true,
"self": 219.62586858200348,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006253553000078682,
"count": 1,
"is_parallel": true,
"self": 0.00435384900038116,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018997039996975218,
"count": 10,
"is_parallel": true,
"self": 0.0018997039996975218
}
}
},
"UnityEnvironment.step": {
"total": 0.035540387999844825,
"count": 1,
"is_parallel": true,
"self": 0.0005724709997139144,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000414909000028274,
"count": 1,
"is_parallel": true,
"self": 0.000414909000028274
},
"communicator.exchange": {
"total": 0.03275579099999959,
"count": 1,
"is_parallel": true,
"self": 0.03275579099999959
},
"steps_from_proto": {
"total": 0.0017972170001030463,
"count": 1,
"is_parallel": true,
"self": 0.0003731000001607754,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001424116999942271,
"count": 10,
"is_parallel": true,
"self": 0.001424116999942271
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 192.69312191198833,
"count": 18191,
"is_parallel": true,
"self": 9.485459921968186,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.252352026994913,
"count": 18191,
"is_parallel": true,
"self": 5.252352026994913
},
"communicator.exchange": {
"total": 147.92656516701618,
"count": 18191,
"is_parallel": true,
"self": 147.92656516701618
},
"steps_from_proto": {
"total": 30.02874479600905,
"count": 18191,
"is_parallel": true,
"self": 5.317919974017514,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.710824821991537,
"count": 181910,
"is_parallel": true,
"self": 24.710824821991537
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.47146452500283,
"count": 18192,
"self": 0.3954675010054416,
"children": {
"process_trajectory": {
"total": 26.84335321899607,
"count": 18192,
"self": 26.447306917996002,
"children": {
"RLTrainer._checkpoint": {
"total": 0.39604630100006943,
"count": 4,
"self": 0.39604630100006943
}
}
},
"_update_policy": {
"total": 93.23264380500132,
"count": 90,
"self": 37.32808372299269,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.90456008200863,
"count": 4587,
"self": 55.90456008200863
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.610000688553555e-07,
"count": 1,
"self": 9.610000688553555e-07
},
"TrainerController._save_models": {
"total": 0.10073483400014993,
"count": 1,
"self": 0.0008575159999963944,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09987731800015354,
"count": 1,
"self": 0.09987731800015354
}
}
}
}
}
}
}