kitrakrev's picture
First Push
58eca89
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9643765091896057,
"min": 0.9643765091896057,
"max": 2.8568971157073975,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9229.0830078125,
"min": 9229.0830078125,
"max": 29257.482421875,
"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": 13.401196479797363,
"min": 0.3606609106063843,
"max": 13.401196479797363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2613.2333984375,
"min": 69.96821594238281,
"max": 2715.135986328125,
"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.Losses.PolicyLoss.mean": {
"value": 0.0665169576448748,
"min": 0.06609426497944856,
"max": 0.07325153478233702,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2660678305794992,
"min": 0.26437705991779425,
"max": 0.3503121538237097,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18422343597254331,
"min": 0.10996767179971999,
"max": 0.2976873995801982,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7368937438901733,
"min": 0.43987068719887995,
"max": 1.4884369979009908,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.0013851600382799997,
"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": 0.9617200000000001,
"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": 26.386363636363637,
"min": 3.5454545454545454,
"max": 26.654545454545456,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1161.0,
"min": 156.0,
"max": 1466.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.386363636363637,
"min": 3.5454545454545454,
"max": 26.654545454545456,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1161.0,
"min": 156.0,
"max": 1466.0,
"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": "1684939759",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684940459"
},
"total": 700.400032217,
"count": 1,
"self": 0.43224161099988123,
"children": {
"run_training.setup": {
"total": 0.06472794400008297,
"count": 1,
"self": 0.06472794400008297
},
"TrainerController.start_learning": {
"total": 699.903062662,
"count": 1,
"self": 0.5472334720047911,
"children": {
"TrainerController._reset_env": {
"total": 6.092389088999994,
"count": 1,
"self": 6.092389088999994
},
"TrainerController.advance": {
"total": 693.1102732399954,
"count": 18204,
"self": 0.2540156770123758,
"children": {
"env_step": {
"total": 692.856257562983,
"count": 18204,
"self": 569.3214323519853,
"children": {
"SubprocessEnvManager._take_step": {
"total": 123.26262340300832,
"count": 18204,
"self": 1.8186170419922973,
"children": {
"TorchPolicy.evaluate": {
"total": 121.44400636101602,
"count": 18204,
"self": 121.44400636101602
}
}
},
"workers": {
"total": 0.2722018079894042,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 698.1257270929854,
"count": 18204,
"is_parallel": true,
"self": 446.09034407197873,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007215707000000293,
"count": 1,
"is_parallel": true,
"self": 0.005159980000030373,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00205572699996992,
"count": 10,
"is_parallel": true,
"self": 0.00205572699996992
}
}
},
"UnityEnvironment.step": {
"total": 0.04348006700001861,
"count": 1,
"is_parallel": true,
"self": 0.0004283670000404527,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003370109999423221,
"count": 1,
"is_parallel": true,
"self": 0.0003370109999423221
},
"communicator.exchange": {
"total": 0.04090162199997849,
"count": 1,
"is_parallel": true,
"self": 0.04090162199997849
},
"steps_from_proto": {
"total": 0.0018130670000573446,
"count": 1,
"is_parallel": true,
"self": 0.0003433330000461865,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001469734000011158,
"count": 10,
"is_parallel": true,
"self": 0.001469734000011158
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 252.03538302100662,
"count": 18203,
"is_parallel": true,
"self": 9.943160405034178,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.270924390985897,
"count": 18203,
"is_parallel": true,
"self": 5.270924390985897
},
"communicator.exchange": {
"total": 203.197301349991,
"count": 18203,
"is_parallel": true,
"self": 203.197301349991
},
"steps_from_proto": {
"total": 33.623996874995555,
"count": 18203,
"is_parallel": true,
"self": 6.451977115057616,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.17201975993794,
"count": 182030,
"is_parallel": true,
"self": 27.17201975993794
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015815799997653812,
"count": 1,
"self": 0.00015815799997653812,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 689.569578271957,
"count": 446992,
"is_parallel": true,
"self": 9.594731304969628,
"children": {
"process_trajectory": {
"total": 253.51996327898746,
"count": 446992,
"is_parallel": true,
"self": 252.4186547599877,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1013085189997582,
"count": 4,
"is_parallel": true,
"self": 1.1013085189997582
}
}
},
"_update_policy": {
"total": 426.4548836879999,
"count": 90,
"is_parallel": true,
"self": 204.9176229860069,
"children": {
"TorchPPOOptimizer.update": {
"total": 221.53726070199298,
"count": 15290,
"is_parallel": true,
"self": 221.53726070199298
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15300870299984126,
"count": 1,
"self": 0.000985133999847676,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15202356899999359,
"count": 1,
"self": 0.15202356899999359
}
}
}
}
}
}
}