imflash217's picture
add an agent trained for HUGGY environment using Unity's
cef80cd
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4103868007659912,
"min": 1.4103868007659912,
"max": 1.4274868965148926,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71443.140625,
"min": 69742.84375,
"max": 75990.296875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.41456166419019,
"min": 71.4536231884058,
"max": 400.344,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49408.0,
"min": 48932.0,
"max": 50043.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999967.0,
"min": 49938.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999967.0,
"min": 49938.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4667954444885254,
"min": -0.016662035137414932,
"max": 2.5525505542755127,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1660.1533203125,
"min": -2.0660922527313232,
"max": 1702.937744140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.747226796391106,
"min": 1.7104184889504987,
"max": 4.082351127291114,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2521.8836339712143,
"min": 212.09189262986183,
"max": 2665.661264896393,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.747226796391106,
"min": 1.7104184889504987,
"max": 4.082351127291114,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2521.8836339712143,
"min": 212.09189262986183,
"max": 2665.661264896393,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015737943868185136,
"min": 0.01311563012774665,
"max": 0.019196001969006223,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.047213831604555404,
"min": 0.0262312602554933,
"max": 0.05622510362039368,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.060821239939994276,
"min": 0.023401581744352976,
"max": 0.06156981810927391,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18246371981998283,
"min": 0.04680316348870595,
"max": 0.18246371981998283,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.8099487300500043e-06,
"min": 3.8099487300500043e-06,
"max": 0.00029523397658867494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1429846190150012e-05,
"min": 1.1429846190150012e-05,
"max": 0.0008438031187322998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126995,
"min": 0.10126995,
"max": 0.19841132499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30380985,
"min": 0.20766155000000003,
"max": 0.5812677000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.337050500000004e-05,
"min": 7.337050500000004e-05,
"max": 0.004920725117500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022011151500000013,
"min": 0.00022011151500000013,
"max": 0.014065258230000002,
"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": "1673661050",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=FlashHuggy --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": "1673663253"
},
"total": 2202.95601411,
"count": 1,
"self": 0.4984824180000942,
"children": {
"run_training.setup": {
"total": 0.10510264100003042,
"count": 1,
"self": 0.10510264100003042
},
"TrainerController.start_learning": {
"total": 2202.352429051,
"count": 1,
"self": 3.664210264992562,
"children": {
"TrainerController._reset_env": {
"total": 9.879400780999958,
"count": 1,
"self": 9.879400780999958
},
"TrainerController.advance": {
"total": 2188.6963218120077,
"count": 233340,
"self": 3.8661988319527154,
"children": {
"env_step": {
"total": 1712.5361720870696,
"count": 233340,
"self": 1441.2899167210371,
"children": {
"SubprocessEnvManager._take_step": {
"total": 268.6797131340286,
"count": 233340,
"self": 14.326780788145015,
"children": {
"TorchPolicy.evaluate": {
"total": 254.35293234588357,
"count": 222978,
"self": 63.47691200385134,
"children": {
"TorchPolicy.sample_actions": {
"total": 190.87602034203223,
"count": 222978,
"self": 190.87602034203223
}
}
}
}
},
"workers": {
"total": 2.5665422320039397,
"count": 233340,
"self": 0.0,
"children": {
"worker_root": {
"total": 2194.637831367027,
"count": 233340,
"is_parallel": true,
"self": 1008.3610153669383,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002358321999963664,
"count": 1,
"is_parallel": true,
"self": 0.00043952100008937123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019188009998742928,
"count": 2,
"is_parallel": true,
"self": 0.0019188009998742928
}
}
},
"UnityEnvironment.step": {
"total": 0.02675768800008882,
"count": 1,
"is_parallel": true,
"self": 0.000281086000313735,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020291299983909994,
"count": 1,
"is_parallel": true,
"self": 0.00020291299983909994
},
"communicator.exchange": {
"total": 0.025579053000001295,
"count": 1,
"is_parallel": true,
"self": 0.025579053000001295
},
"steps_from_proto": {
"total": 0.0006946359999346896,
"count": 1,
"is_parallel": true,
"self": 0.00023630999976376188,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00045832600017092773,
"count": 2,
"is_parallel": true,
"self": 0.00045832600017092773
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1186.2768160000887,
"count": 233339,
"is_parallel": true,
"self": 34.36141450505011,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 74.08560208303675,
"count": 233339,
"is_parallel": true,
"self": 74.08560208303675
},
"communicator.exchange": {
"total": 986.3778589650656,
"count": 233339,
"is_parallel": true,
"self": 986.3778589650656
},
"steps_from_proto": {
"total": 91.4519404469363,
"count": 233339,
"is_parallel": true,
"self": 37.22075322982323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.231187217113074,
"count": 466678,
"is_parallel": true,
"self": 54.231187217113074
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 472.2939508929853,
"count": 233340,
"self": 5.754786818084767,
"children": {
"process_trajectory": {
"total": 152.35628253490108,
"count": 233340,
"self": 151.20495878690167,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1513237479994132,
"count": 10,
"self": 1.1513237479994132
}
}
},
"_update_policy": {
"total": 314.18288153999947,
"count": 97,
"self": 260.9766535370147,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.206228002984744,
"count": 2910,
"self": 53.206228002984744
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.100000741251279e-07,
"count": 1,
"self": 8.100000741251279e-07
},
"TrainerController._save_models": {
"total": 0.11249538299989581,
"count": 1,
"self": 0.001960001000043121,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11053538199985269,
"count": 1,
"self": 0.11053538199985269
}
}
}
}
}
}
}