ppo-Huggy / run_logs /timers.json
codeslord's picture
Huggy PPO Model
8938100
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4081000089645386,
"min": 1.4081000089645386,
"max": 1.4299530982971191,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69841.7578125,
"min": 67501.7421875,
"max": 78196.6328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.76666666666667,
"min": 77.8596214511041,
"max": 437.4086956521739,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49457.0,
"min": 48663.0,
"max": 50302.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999959.0,
"min": 49874.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999959.0,
"min": 49874.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4446990489959717,
"min": 0.1273852288722992,
"max": 2.482417583465576,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1393.4783935546875,
"min": 14.521915435791016,
"max": 1504.835693359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7344157694724567,
"min": 1.7468783135215442,
"max": 3.9752108208806796,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2128.6169885993004,
"min": 199.14412774145603,
"max": 2396.8049979805946,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7344157694724567,
"min": 1.7468783135215442,
"max": 3.9752108208806796,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2128.6169885993004,
"min": 199.14412774145603,
"max": 2396.8049979805946,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016612314598751256,
"min": 0.014091565635074705,
"max": 0.0207025105706028,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.049836943796253766,
"min": 0.02818313127014941,
"max": 0.05853524556247673,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05167203586962488,
"min": 0.02144774418945114,
"max": 0.06120061824719111,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15501610760887463,
"min": 0.04289548837890228,
"max": 0.18360185474157334,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.330298889933328e-06,
"min": 3.330298889933328e-06,
"max": 0.0002953074765641749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.990896669799984e-06,
"min": 9.990896669799984e-06,
"max": 0.00084378586873805,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111006666666666,
"min": 0.10111006666666666,
"max": 0.19843582499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033302,
"min": 0.2073619,
"max": 0.58126195,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.539232666666656e-05,
"min": 6.539232666666656e-05,
"max": 0.0049219476675,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001961769799999997,
"min": 0.0001961769799999997,
"max": 0.014064971305000002,
"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": "1675490905",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675493180"
},
"total": 2274.601178868,
"count": 1,
"self": 0.39250095700026577,
"children": {
"run_training.setup": {
"total": 0.1041640420000931,
"count": 1,
"self": 0.1041640420000931
},
"TrainerController.start_learning": {
"total": 2274.1045138689997,
"count": 1,
"self": 4.103907400002299,
"children": {
"TrainerController._reset_env": {
"total": 10.268402244999834,
"count": 1,
"self": 10.268402244999834
},
"TrainerController.advance": {
"total": 2259.6129744139976,
"count": 232285,
"self": 4.256535097015785,
"children": {
"env_step": {
"total": 1796.8512433909693,
"count": 232285,
"self": 1504.1931874610007,
"children": {
"SubprocessEnvManager._take_step": {
"total": 289.9501314369661,
"count": 232285,
"self": 15.192215513943438,
"children": {
"TorchPolicy.evaluate": {
"total": 274.75791592302267,
"count": 222934,
"self": 68.87547410901584,
"children": {
"TorchPolicy.sample_actions": {
"total": 205.88244181400682,
"count": 222934,
"self": 205.88244181400682
}
}
}
}
},
"workers": {
"total": 2.707924493002565,
"count": 232285,
"self": 0.0,
"children": {
"worker_root": {
"total": 2265.9250232930594,
"count": 232285,
"is_parallel": true,
"self": 1033.1316294991043,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023039810000682337,
"count": 1,
"is_parallel": true,
"self": 0.0003823740000825637,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00192160699998567,
"count": 2,
"is_parallel": true,
"self": 0.00192160699998567
}
}
},
"UnityEnvironment.step": {
"total": 0.02884424300009414,
"count": 1,
"is_parallel": true,
"self": 0.00027946600016548473,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022288200011644221,
"count": 1,
"is_parallel": true,
"self": 0.00022288200011644221
},
"communicator.exchange": {
"total": 0.0275939829998606,
"count": 1,
"is_parallel": true,
"self": 0.0275939829998606
},
"steps_from_proto": {
"total": 0.0007479119999516115,
"count": 1,
"is_parallel": true,
"self": 0.00024089099997581798,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005070209999757935,
"count": 2,
"is_parallel": true,
"self": 0.0005070209999757935
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1232.7933937939551,
"count": 232284,
"is_parallel": true,
"self": 35.37760655705824,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.33032190387962,
"count": 232284,
"is_parallel": true,
"self": 82.33032190387962
},
"communicator.exchange": {
"total": 1020.2407904619492,
"count": 232284,
"is_parallel": true,
"self": 1020.2407904619492
},
"steps_from_proto": {
"total": 94.84467487106804,
"count": 232284,
"is_parallel": true,
"self": 41.54688695907407,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.297787911993964,
"count": 464568,
"is_parallel": true,
"self": 53.297787911993964
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 458.5051959260122,
"count": 232285,
"self": 6.472776297955306,
"children": {
"process_trajectory": {
"total": 149.69489626105633,
"count": 232285,
"self": 148.58693690205564,
"children": {
"RLTrainer._checkpoint": {
"total": 1.107959359000688,
"count": 10,
"self": 1.107959359000688
}
}
},
"_update_policy": {
"total": 302.3375233670006,
"count": 97,
"self": 249.20140541098067,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.136117956019916,
"count": 2910,
"self": 53.136117956019916
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.78999651124468e-07,
"count": 1,
"self": 9.78999651124468e-07
},
"TrainerController._save_models": {
"total": 0.11922883100032777,
"count": 1,
"self": 0.0019895790001100977,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11723925200021768,
"count": 1,
"self": 0.11723925200021768
}
}
}
}
}
}
}