rootacess's picture
First Push
7acd766
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4412913918495178,
"min": 0.4340583086013794,
"max": 1.4364012479782104,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13125.771484375,
"min": 13125.771484375,
"max": 43574.66796875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989969.0,
"min": 29917.0,
"max": 989969.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989969.0,
"min": 29917.0,
"max": 989969.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6832131147384644,
"min": -0.06457571685314178,
"max": 0.7111125588417053,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 196.765380859375,
"min": -15.627324104309082,
"max": 204.421875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02027186006307602,
"min": -0.0043133702129125595,
"max": 0.44754379987716675,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.838295936584473,
"min": -1.2508773803710938,
"max": 106.06787872314453,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06923499788085576,
"min": 0.06493895529170653,
"max": 0.07448410819527715,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9692899703319805,
"min": 0.5958728655622172,
"max": 1.0718011139542798,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016361641161936512,
"min": 0.003175389624326709,
"max": 0.017926438399849254,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2290629762671112,
"min": 0.04445545474057393,
"max": 0.2688965759977388,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.646411736942857e-06,
"min": 7.646411736942857e-06,
"max": 0.0002948439392186875,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010704976431720001,
"min": 0.00010704976431720001,
"max": 0.0038831320056226986,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254877142857144,
"min": 0.10254877142857144,
"max": 0.1982813125,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4356828000000001,
"min": 1.4356828000000001,
"max": 2.6943773,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026462226571428575,
"min": 0.00026462226571428575,
"max": 0.00982830311875,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003704711720000001,
"min": 0.003704711720000001,
"max": 0.12944829227000004,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01510715950280428,
"min": 0.01510715950280428,
"max": 0.5159338116645813,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.21150022745132446,
"min": 0.21150022745132446,
"max": 4.12747049331665,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 271.3063063063063,
"min": 266.287037037037,
"max": 960.7058823529412,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30115.0,
"min": 16332.0,
"max": 33522.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7106702515670844,
"min": -0.8440000502502217,
"max": 1.7258867756375726,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 189.88439792394638,
"min": -21.668001651763916,
"max": 189.88439792394638,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7106702515670844,
"min": -0.8440000502502217,
"max": 1.7258867756375726,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 189.88439792394638,
"min": -21.668001651763916,
"max": 189.88439792394638,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04237307859207126,
"min": 0.04184416155780623,
"max": 9.665765928871492,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.70341172371991,
"min": 4.5872240486205555,
"max": 164.31802079081535,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674150056",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
"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": "1674152285"
},
"total": 2228.85885203,
"count": 1,
"self": 0.47823352099976546,
"children": {
"run_training.setup": {
"total": 0.17913618600005066,
"count": 1,
"self": 0.17913618600005066
},
"TrainerController.start_learning": {
"total": 2228.201482323,
"count": 1,
"self": 1.5960359260325276,
"children": {
"TrainerController._reset_env": {
"total": 6.092566447000081,
"count": 1,
"self": 6.092566447000081
},
"TrainerController.advance": {
"total": 2220.4282593789676,
"count": 64494,
"self": 1.5551070248839096,
"children": {
"env_step": {
"total": 1566.4666141500547,
"count": 64494,
"self": 1453.0127112600653,
"children": {
"SubprocessEnvManager._take_step": {
"total": 112.56315711903267,
"count": 64494,
"self": 4.557326625086262,
"children": {
"TorchPolicy.evaluate": {
"total": 108.0058304939464,
"count": 62545,
"self": 35.87953468089768,
"children": {
"TorchPolicy.sample_actions": {
"total": 72.12629581304873,
"count": 62545,
"self": 72.12629581304873
}
}
}
}
},
"workers": {
"total": 0.8907457709567552,
"count": 64494,
"self": 0.0,
"children": {
"worker_root": {
"total": 2223.313556813987,
"count": 64494,
"is_parallel": true,
"self": 876.7842009499461,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001814872000068135,
"count": 1,
"is_parallel": true,
"self": 0.0006748249998054234,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011400470002627117,
"count": 8,
"is_parallel": true,
"self": 0.0011400470002627117
}
}
},
"UnityEnvironment.step": {
"total": 0.04370950499992432,
"count": 1,
"is_parallel": true,
"self": 0.0005689919998985715,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000411662000033175,
"count": 1,
"is_parallel": true,
"self": 0.000411662000033175
},
"communicator.exchange": {
"total": 0.04079902100011168,
"count": 1,
"is_parallel": true,
"self": 0.04079902100011168
},
"steps_from_proto": {
"total": 0.0019298299998808943,
"count": 1,
"is_parallel": true,
"self": 0.0007283350000761857,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012014949998047086,
"count": 8,
"is_parallel": true,
"self": 0.0012014949998047086
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1346.5293558640408,
"count": 64493,
"is_parallel": true,
"self": 28.30090187509859,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.638689866010964,
"count": 64493,
"is_parallel": true,
"self": 21.638689866010964
},
"communicator.exchange": {
"total": 1195.2977823119818,
"count": 64493,
"is_parallel": true,
"self": 1195.2977823119818
},
"steps_from_proto": {
"total": 101.29198181094944,
"count": 64493,
"is_parallel": true,
"self": 22.94714774483532,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.34483406611412,
"count": 515944,
"is_parallel": true,
"self": 78.34483406611412
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 652.4065382040292,
"count": 64494,
"self": 2.921331394948993,
"children": {
"process_trajectory": {
"total": 145.48115407007595,
"count": 64494,
"self": 145.2973158370762,
"children": {
"RLTrainer._checkpoint": {
"total": 0.183838232999733,
"count": 2,
"self": 0.183838232999733
}
}
},
"_update_policy": {
"total": 504.00405273900424,
"count": 464,
"self": 191.38586028095688,
"children": {
"TorchPPOOptimizer.update": {
"total": 312.61819245804736,
"count": 22770,
"self": 312.61819245804736
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.619999789516442e-07,
"count": 1,
"self": 8.619999789516442e-07
},
"TrainerController._save_models": {
"total": 0.0846197089999805,
"count": 1,
"self": 0.0016932979997363873,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08292641100024412,
"count": 1,
"self": 0.08292641100024412
}
}
}
}
}
}
}