VinayHajare's picture
Uploaded the SnowballTarget ML-agent
80c0aab
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9801990985870361,
"min": 0.9801990985870361,
"max": 2.870183229446411,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9445.1982421875,
"min": 9445.1982421875,
"max": 29488.26171875,
"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": 12.680135726928711,
"min": 0.4458877444267273,
"max": 12.680135726928711,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2472.62646484375,
"min": 86.5022201538086,
"max": 2576.146484375,
"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": 0.0617823747410262,
"min": 0.0617823747410262,
"max": 0.07601295279055906,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2471294989641048,
"min": 0.2471294989641048,
"max": 0.3800647639527953,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18773524280564458,
"min": 0.11656352364476405,
"max": 0.2759586895797767,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7509409712225783,
"min": 0.4662540945790562,
"max": 1.3797934478988836,
"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": 25.34090909090909,
"min": 3.6136363636363638,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 159.0,
"max": 1365.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.6136363636363638,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 159.0,
"max": 1365.0,
"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": "1700219767",
"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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700220365"
},
"total": 597.914479302,
"count": 1,
"self": 0.8827325270001438,
"children": {
"run_training.setup": {
"total": 0.055677141999979085,
"count": 1,
"self": 0.055677141999979085
},
"TrainerController.start_learning": {
"total": 596.976069633,
"count": 1,
"self": 0.8184315629971479,
"children": {
"TrainerController._reset_env": {
"total": 1.8882795849999638,
"count": 1,
"self": 1.8882795849999638
},
"TrainerController.advance": {
"total": 594.1247079490029,
"count": 18223,
"self": 0.41319718700174235,
"children": {
"env_step": {
"total": 593.7115107620011,
"count": 18223,
"self": 467.3295322019981,
"children": {
"SubprocessEnvManager._take_step": {
"total": 125.97283186599668,
"count": 18223,
"self": 2.5565401199930875,
"children": {
"TorchPolicy.evaluate": {
"total": 123.4162917460036,
"count": 18223,
"self": 123.4162917460036
}
}
},
"workers": {
"total": 0.4091466940063242,
"count": 18223,
"self": 0.0,
"children": {
"worker_root": {
"total": 594.8507124359969,
"count": 18223,
"is_parallel": true,
"self": 271.66868669000615,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007509867999999642,
"count": 1,
"is_parallel": true,
"self": 0.0052443280000034065,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022655399999962356,
"count": 10,
"is_parallel": true,
"self": 0.0022655399999962356
}
}
},
"UnityEnvironment.step": {
"total": 0.07633147400002827,
"count": 1,
"is_parallel": true,
"self": 0.0007574109999950451,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004506370000285642,
"count": 1,
"is_parallel": true,
"self": 0.0004506370000285642
},
"communicator.exchange": {
"total": 0.06294331999998803,
"count": 1,
"is_parallel": true,
"self": 0.06294331999998803
},
"steps_from_proto": {
"total": 0.012180106000016622,
"count": 1,
"is_parallel": true,
"self": 0.000542196000083095,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.011637909999933527,
"count": 10,
"is_parallel": true,
"self": 0.011637909999933527
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 323.18202574599076,
"count": 18222,
"is_parallel": true,
"self": 14.538208941988216,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.6367996810033105,
"count": 18222,
"is_parallel": true,
"self": 7.6367996810033105
},
"communicator.exchange": {
"total": 255.765995588,
"count": 18222,
"is_parallel": true,
"self": 255.765995588
},
"steps_from_proto": {
"total": 45.24102153499922,
"count": 18222,
"is_parallel": true,
"self": 8.945397039992656,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.295624495006564,
"count": 182220,
"is_parallel": true,
"self": 36.295624495006564
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001828990000376507,
"count": 1,
"self": 0.0001828990000376507,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 588.7911795299594,
"count": 613341,
"is_parallel": true,
"self": 14.213190488971804,
"children": {
"process_trajectory": {
"total": 321.5221471709884,
"count": 613341,
"is_parallel": true,
"self": 320.1428514429886,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3792957279997609,
"count": 4,
"is_parallel": true,
"self": 1.3792957279997609
}
}
},
"_update_policy": {
"total": 253.05584186999926,
"count": 90,
"is_parallel": true,
"self": 75.63754796799435,
"children": {
"TorchPPOOptimizer.update": {
"total": 177.4182939020049,
"count": 4587,
"is_parallel": true,
"self": 177.4182939020049
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14446763699993426,
"count": 1,
"self": 0.001737316000003375,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14273032099993088,
"count": 1,
"self": 0.14273032099993088
}
}
}
}
}
}
}