ppo-Huggy / run_logs /timers.json
seynath's picture
Trained Huggy to fetch stick
6b042eb verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408841609954834,
"min": 1.408841609954834,
"max": 1.4274191856384277,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71808.65625,
"min": 68807.71875,
"max": 76980.5,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.9626334519573,
"min": 87.72291296625222,
"max": 380.87786259541986,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49435.0,
"min": 48776.0,
"max": 50211.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999971.0,
"min": 49635.0,
"max": 1999971.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999971.0,
"min": 49635.0,
"max": 1999971.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3534774780273438,
"min": 0.1470765471458435,
"max": 2.419691801071167,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1322.654296875,
"min": 19.119951248168945,
"max": 1348.46044921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6585619358405523,
"min": 1.9481795384333684,
"max": 3.92381972805854,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2056.1118079423904,
"min": 253.2633399963379,
"max": 2107.5222704410553,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6585619358405523,
"min": 1.9481795384333684,
"max": 3.92381972805854,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2056.1118079423904,
"min": 253.2633399963379,
"max": 2107.5222704410553,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018083307096902798,
"min": 0.013498218409828648,
"max": 0.021099030579595515,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.054249921290708394,
"min": 0.026996436819657296,
"max": 0.058400487441880006,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.059260476960076226,
"min": 0.02262524977947275,
"max": 0.059260476960076226,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17778143088022869,
"min": 0.0452504995589455,
"max": 0.17778143088022869,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.288498903866669e-06,
"min": 3.288498903866669e-06,
"max": 0.0002953488015504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.865496711600007e-06,
"min": 9.865496711600007e-06,
"max": 0.0008439657186781,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109613333333334,
"min": 0.10109613333333334,
"max": 0.1984496,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032884,
"min": 0.20733710000000005,
"max": 0.5813219,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.469705333333339e-05,
"min": 6.469705333333339e-05,
"max": 0.0049226350400000006,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019409116000000017,
"min": 0.00019409116000000017,
"max": 0.014067962809999997,
"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": "1765992978",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/root/miniconda/envs/mlagents/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1765995533"
},
"total": 2554.445363013,
"count": 1,
"self": 0.4870411570000215,
"children": {
"run_training.setup": {
"total": 0.02090856699987853,
"count": 1,
"self": 0.02090856699987853
},
"TrainerController.start_learning": {
"total": 2553.9374132890002,
"count": 1,
"self": 4.216761246986607,
"children": {
"TrainerController._reset_env": {
"total": 3.555080124000142,
"count": 1,
"self": 3.555080124000142
},
"TrainerController.advance": {
"total": 2546.051651255014,
"count": 232265,
"self": 4.49936748491109,
"children": {
"env_step": {
"total": 2084.642110084975,
"count": 232265,
"self": 1679.7872257785903,
"children": {
"SubprocessEnvManager._take_step": {
"total": 402.176612271207,
"count": 232265,
"self": 15.459253022339908,
"children": {
"TorchPolicy.evaluate": {
"total": 386.71735924886707,
"count": 223024,
"self": 386.71735924886707
}
}
},
"workers": {
"total": 2.6782720351775424,
"count": 232265,
"self": 0.0,
"children": {
"worker_root": {
"total": 2541.121190285126,
"count": 232265,
"is_parallel": true,
"self": 1181.757443151053,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000886374999936379,
"count": 1,
"is_parallel": true,
"self": 0.00027282700011710403,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000613547999819275,
"count": 2,
"is_parallel": true,
"self": 0.000613547999819275
}
}
},
"UnityEnvironment.step": {
"total": 0.029383094999957393,
"count": 1,
"is_parallel": true,
"self": 0.00035294000008434523,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019271300016043824,
"count": 1,
"is_parallel": true,
"self": 0.00019271300016043824
},
"communicator.exchange": {
"total": 0.028175183999792353,
"count": 1,
"is_parallel": true,
"self": 0.028175183999792353
},
"steps_from_proto": {
"total": 0.0006622579999202571,
"count": 1,
"is_parallel": true,
"self": 0.0001845599999796832,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047769799994057394,
"count": 2,
"is_parallel": true,
"self": 0.00047769799994057394
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1359.363747134073,
"count": 232264,
"is_parallel": true,
"self": 38.764195510131685,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.17068399013124,
"count": 232264,
"is_parallel": true,
"self": 83.17068399013124
},
"communicator.exchange": {
"total": 1147.4427863347942,
"count": 232264,
"is_parallel": true,
"self": 1147.4427863347942
},
"steps_from_proto": {
"total": 89.98608129901595,
"count": 232264,
"is_parallel": true,
"self": 32.44585138789307,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.54022991112288,
"count": 464528,
"is_parallel": true,
"self": 57.54022991112288
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 456.91017368512803,
"count": 232265,
"self": 6.382794666123573,
"children": {
"process_trajectory": {
"total": 152.80591488500477,
"count": 232265,
"self": 151.63182389300437,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1740909920004015,
"count": 10,
"self": 1.1740909920004015
}
}
},
"_update_policy": {
"total": 297.7214641339997,
"count": 97,
"self": 235.66629511796464,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.05516901603505,
"count": 2910,
"self": 62.05516901603505
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.489998097298667e-07,
"count": 1,
"self": 7.489998097298667e-07
},
"TrainerController._save_models": {
"total": 0.11391991399977996,
"count": 1,
"self": 0.0012880919994131546,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11263182200036681,
"count": 1,
"self": 0.11263182200036681
}
}
}
}
}
}
}