|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.1452857255935669, |
|
"min": 0.1444326788187027, |
|
"max": 1.0461056232452393, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 14516.9501953125, |
|
"min": 14408.603515625, |
|
"max": 105480.921875, |
|
"count": 30 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999952.0, |
|
"min": 99900.0, |
|
"max": 2999952.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999952.0, |
|
"min": 99900.0, |
|
"max": 2999952.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7961941361427307, |
|
"min": -0.0913986787199974, |
|
"max": 0.8202935457229614, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 799.37890625, |
|
"min": -73.21034240722656, |
|
"max": 838.3400268554688, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.01836739480495453, |
|
"min": 0.011664221063256264, |
|
"max": 0.42849498987197876, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 18.44086456298828, |
|
"min": 10.91771125793457, |
|
"max": 343.2244873046875, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.04557692741971886, |
|
"min": 0.044100132224881516, |
|
"max": 0.04938360436981319, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 2.1421155887267864, |
|
"min": 1.7700796656169053, |
|
"max": 2.32102940538122, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014917593240467103, |
|
"min": 0.001749484076883257, |
|
"max": 0.01596666678354571, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.7011268823019539, |
|
"min": 0.07697729938286331, |
|
"max": 0.7664000056101941, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 5.054864272524822e-06, |
|
"min": 5.054864272524822e-06, |
|
"max": 0.00029441628023961887, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00023757862080866663, |
|
"min": 0.00023757862080866663, |
|
"max": 0.012536508721163832, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10168492198581561, |
|
"min": 0.10168492198581561, |
|
"max": 0.19813875945945947, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 4.779191333333333, |
|
"min": 4.779191333333333, |
|
"max": 8.850994833333331, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0001783237063829787, |
|
"min": 0.0001783237063829787, |
|
"max": 0.00981406207, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.008381214199999999, |
|
"min": 0.008381214199999999, |
|
"max": 0.41790573304999995, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011397403664886951, |
|
"min": 0.011397403664886951, |
|
"max": 0.41011297702789307, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.535677969455719, |
|
"min": 0.535677969455719, |
|
"max": 15.174180030822754, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 228.13636363636363, |
|
"min": 225.97972972972974, |
|
"max": 970.58, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 100380.0, |
|
"min": 95066.0, |
|
"max": 105186.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7580970254533654, |
|
"min": -0.8314020502567291, |
|
"max": 1.7695135027673599, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 771.8045941740274, |
|
"min": -83.14020502567291, |
|
"max": 785.6639952287078, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7580970254533654, |
|
"min": -0.8314020502567291, |
|
"max": 1.7695135027673599, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 771.8045941740274, |
|
"min": -83.14020502567291, |
|
"max": 785.6639952287078, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.026805186059153167, |
|
"min": 0.0267875842717429, |
|
"max": 5.570993026376379, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 11.76747667996824, |
|
"min": 11.76747667996824, |
|
"max": 545.9573165848851, |
|
"count": 30 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 30 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1698302067", |
|
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", |
|
"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": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.1.0+cu118", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1698308732" |
|
}, |
|
"total": 6664.740312280999, |
|
"count": 1, |
|
"self": 0.4764733289994183, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04820331299993086, |
|
"count": 1, |
|
"self": 0.04820331299993086 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 6664.215635639, |
|
"count": 1, |
|
"self": 4.06504375802524, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.5561451600000282, |
|
"count": 1, |
|
"self": 3.5561451600000282 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 6656.399910853975, |
|
"count": 194037, |
|
"self": 4.242367065165126, |
|
"children": { |
|
"env_step": { |
|
"total": 5125.678803261965, |
|
"count": 194037, |
|
"self": 4720.557824530886, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 402.57981815115886, |
|
"count": 194037, |
|
"self": 13.70290741616509, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 388.87691073499377, |
|
"count": 187553, |
|
"self": 388.87691073499377 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.541160579919847, |
|
"count": 194037, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 6649.856148793965, |
|
"count": 194037, |
|
"is_parallel": true, |
|
"self": 2281.8795569861595, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.002027706000035323, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006951670000034937, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013325390000318293, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013325390000318293 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.051519338000048265, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007017410000571545, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005178510000405367, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005178510000405367 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04835310999999365, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04835310999999365 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001946635999956925, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003885129998479897, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015581230001089352, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015581230001089352 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4367.976591807806, |
|
"count": 194036, |
|
"is_parallel": true, |
|
"self": 104.49015878964565, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 76.59239168000659, |
|
"count": 194036, |
|
"is_parallel": true, |
|
"self": 76.59239168000659 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3878.2163948711886, |
|
"count": 194036, |
|
"is_parallel": true, |
|
"self": 3878.2163948711886 |
|
}, |
|
"steps_from_proto": { |
|
"total": 308.67764646696446, |
|
"count": 194036, |
|
"is_parallel": true, |
|
"self": 63.063819836330936, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 245.61382663063353, |
|
"count": 1552288, |
|
"is_parallel": true, |
|
"self": 245.61382663063353 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1526.4787405268444, |
|
"count": 194037, |
|
"self": 8.300756505722347, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 384.3061853591312, |
|
"count": 194037, |
|
"self": 383.27077805013187, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 1.0354073089993108, |
|
"count": 6, |
|
"self": 1.0354073089993108 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1133.8717986619909, |
|
"count": 1401, |
|
"self": 771.6201021579741, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 362.25169650401676, |
|
"count": 33972, |
|
"self": 362.25169650401676 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1470001481939107e-06, |
|
"count": 1, |
|
"self": 1.1470001481939107e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.19453471999986505, |
|
"count": 1, |
|
"self": 0.007809609999640088, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.18672511000022496, |
|
"count": 1, |
|
"self": 0.18672511000022496 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |