ppo-Huggy-v0 / run_logs /timers.json
darthPanda's picture
Huggy
829b3b4
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4029674530029297,
"min": 1.4029674530029297,
"max": 1.4288406372070312,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71143.078125,
"min": 68902.6796875,
"max": 78195.796875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.2943469785575,
"min": 88.0711743772242,
"max": 406.19354838709677,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49399.0,
"min": 49162.0,
"max": 50368.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999934.0,
"min": 49885.0,
"max": 1999934.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999934.0,
"min": 49885.0,
"max": 1999934.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4295265674591064,
"min": 0.1461886465549469,
"max": 2.4608325958251953,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1248.776611328125,
"min": 17.981203079223633,
"max": 1330.887451171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7987032293809526,
"min": 1.841255687601198,
"max": 3.934413918640823,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1952.5334599018097,
"min": 226.47444957494736,
"max": 2080.0755073428154,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7987032293809526,
"min": 1.841255687601198,
"max": 3.934413918640823,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1952.5334599018097,
"min": 226.47444957494736,
"max": 2080.0755073428154,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017413303231781658,
"min": 0.01409489274568235,
"max": 0.020056781049546165,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05223990969534498,
"min": 0.0281897854913647,
"max": 0.054392584460583746,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04760558826641904,
"min": 0.02148533935348193,
"max": 0.054793112662931284,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14281676479925712,
"min": 0.04297067870696386,
"max": 0.1641352165490389,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5373488209166587e-06,
"min": 3.5373488209166587e-06,
"max": 0.00029531835156054997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0612046462749976e-05,
"min": 1.0612046462749976e-05,
"max": 0.00084415696861435,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117908333333332,
"min": 0.10117908333333332,
"max": 0.19843945000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30353725,
"min": 0.20752699999999996,
"max": 0.58138565,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.883625833333322e-05,
"min": 6.883625833333322e-05,
"max": 0.004922128555,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020650877499999964,
"min": 0.00020650877499999964,
"max": 0.014071143934999999,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1689006694",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/home/darth/MLAI-projects/Huggy_RL/envrl/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1689008686"
},
"total": 1991.7789146660002,
"count": 1,
"self": 0.3536202239997692,
"children": {
"run_training.setup": {
"total": 0.05526191699982519,
"count": 1,
"self": 0.05526191699982519
},
"TrainerController.start_learning": {
"total": 1991.3700325250006,
"count": 1,
"self": 5.08261498298225,
"children": {
"TrainerController._reset_env": {
"total": 25.331067733000054,
"count": 1,
"self": 25.331067733000054
},
"TrainerController.advance": {
"total": 1960.6906988750188,
"count": 231798,
"self": 4.942142751048323,
"children": {
"env_step": {
"total": 1512.9414500538505,
"count": 231798,
"self": 1189.5590773922158,
"children": {
"SubprocessEnvManager._take_step": {
"total": 320.226840767707,
"count": 231798,
"self": 16.508981510827198,
"children": {
"TorchPolicy.evaluate": {
"total": 303.7178592568798,
"count": 223022,
"self": 303.7178592568798
}
}
},
"workers": {
"total": 3.155531893927673,
"count": 231798,
"self": 0.0,
"children": {
"worker_root": {
"total": 1983.6235911119875,
"count": 231798,
"is_parallel": true,
"self": 1049.5264099370365,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013558819996433158,
"count": 1,
"is_parallel": true,
"self": 0.00018456999941918184,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001171312000224134,
"count": 2,
"is_parallel": true,
"self": 0.001171312000224134
}
}
},
"UnityEnvironment.step": {
"total": 0.018546598999819253,
"count": 1,
"is_parallel": true,
"self": 0.00016059299969128915,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00012731000015264726,
"count": 1,
"is_parallel": true,
"self": 0.00012731000015264726
},
"communicator.exchange": {
"total": 0.017871692999960942,
"count": 1,
"is_parallel": true,
"self": 0.017871692999960942
},
"steps_from_proto": {
"total": 0.00038700300001437427,
"count": 1,
"is_parallel": true,
"self": 0.00011718699988705339,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0002698160001273209,
"count": 2,
"is_parallel": true,
"self": 0.0002698160001273209
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 934.097181174951,
"count": 231797,
"is_parallel": true,
"self": 29.452192594944336,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 48.287564690980616,
"count": 231797,
"is_parallel": true,
"self": 48.287564690980616
},
"communicator.exchange": {
"total": 786.2719407777463,
"count": 231797,
"is_parallel": true,
"self": 786.2719407777463
},
"steps_from_proto": {
"total": 70.0854831112797,
"count": 231797,
"is_parallel": true,
"self": 26.28530120796904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 43.80018190331066,
"count": 463594,
"is_parallel": true,
"self": 43.80018190331066
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 442.80710607011997,
"count": 231798,
"self": 7.198759368029641,
"children": {
"process_trajectory": {
"total": 120.26445562209256,
"count": 231798,
"self": 117.04397860609151,
"children": {
"RLTrainer._checkpoint": {
"total": 3.220477016001041,
"count": 10,
"self": 3.220477016001041
}
}
},
"_update_policy": {
"total": 315.3438910799978,
"count": 97,
"self": 269.095691213005,
"children": {
"TorchPPOOptimizer.update": {
"total": 46.24819986699276,
"count": 2910,
"self": 46.24819986699276
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.369997885893099e-07,
"count": 1,
"self": 8.369997885893099e-07
},
"TrainerController._save_models": {
"total": 0.2656500969997069,
"count": 1,
"self": 0.0017605779994482873,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2638895190002586,
"count": 1,
"self": 0.2638895190002586
}
}
}
}
}
}
}