|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.5392292141914368, |
|
"min": 0.5392292141914368, |
|
"max": 1.3762880563735962, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 16038.8330078125, |
|
"min": 16038.8330078125, |
|
"max": 41751.07421875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989905.0, |
|
"min": 29952.0, |
|
"max": 989905.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989905.0, |
|
"min": 29952.0, |
|
"max": 989905.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.12375917285680771, |
|
"min": -0.10935390740633011, |
|
"max": 0.27559468150138855, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 31.063552856445312, |
|
"min": -26.135583877563477, |
|
"max": 65.3159408569336, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.03846127912402153, |
|
"min": 0.01337270624935627, |
|
"max": 0.35965967178344727, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 9.653780937194824, |
|
"min": 3.3164310455322266, |
|
"max": 86.31832122802734, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07064416863589572, |
|
"min": 0.06549117608561314, |
|
"max": 0.07457250677349035, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0596625295384359, |
|
"min": 0.4805440582256716, |
|
"max": 1.0596625295384359, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.00614799391438116, |
|
"min": 0.00011006560505229133, |
|
"max": 0.009394352461179197, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.0922199087157174, |
|
"min": 0.0015409184707320786, |
|
"max": 0.10508711506051494, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.4897975034333325e-06, |
|
"min": 7.4897975034333325e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011234696255149998, |
|
"min": 0.00011234696255149998, |
|
"max": 0.0032558279147240996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10249656666666668, |
|
"min": 0.10249656666666668, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5374485000000002, |
|
"min": 1.3886848, |
|
"max": 2.4434376000000007, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002594070099999999, |
|
"min": 0.0002594070099999999, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003891105149999999, |
|
"min": 0.003891105149999999, |
|
"max": 0.10854906241000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01595507189631462, |
|
"min": 0.01577533408999443, |
|
"max": 0.4828554093837738, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2393260896205902, |
|
"min": 0.22085466980934143, |
|
"max": 3.379987955093384, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 742.6511627906976, |
|
"min": 742.6511627906976, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31934.0, |
|
"min": 15984.0, |
|
"max": 32923.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.3268185652965723, |
|
"min": -1.0000000521540642, |
|
"max": 0.45947022897166173, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 14.05319830775261, |
|
"min": -31.998401656746864, |
|
"max": 17.000398471951485, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.3268185652965723, |
|
"min": -1.0000000521540642, |
|
"max": 0.45947022897166173, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 14.05319830775261, |
|
"min": -31.998401656746864, |
|
"max": 17.000398471951485, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.1215952348659833, |
|
"min": 0.1215952348659833, |
|
"max": 9.277738269418478, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.228595099237282, |
|
"min": 4.518147401162423, |
|
"max": 148.44381231069565, |
|
"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": "1689532314", |
|
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1689534416" |
|
}, |
|
"total": 2101.7249607689996, |
|
"count": 1, |
|
"self": 0.5251996839992898, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04021469799999977, |
|
"count": 1, |
|
"self": 0.04021469799999977 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2101.1595463870003, |
|
"count": 1, |
|
"self": 1.1981772910171458, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.708219864000057, |
|
"count": 1, |
|
"self": 4.708219864000057 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2095.157421332984, |
|
"count": 63191, |
|
"self": 1.252410491955743, |
|
"children": { |
|
"env_step": { |
|
"total": 1460.8306770980244, |
|
"count": 63191, |
|
"self": 1355.29740911211, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 104.79497708794725, |
|
"count": 63191, |
|
"self": 4.614229700891883, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 100.18074738705536, |
|
"count": 62561, |
|
"self": 100.18074738705536 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7382908979670901, |
|
"count": 63191, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2096.631769648029, |
|
"count": 63191, |
|
"is_parallel": true, |
|
"self": 849.4502458101242, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001735353999720246, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005094829998597561, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.00122587099986049, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.00122587099986049 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.10125496799992106, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005956850000075065, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00045543900023403694, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00045543900023403694 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.09827383399988321, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.09827383399988321 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0019300099997963116, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00035073199887847295, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015792780009178387, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015792780009178387 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1247.181523837905, |
|
"count": 63190, |
|
"is_parallel": true, |
|
"self": 33.79419163083503, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.133726682954148, |
|
"count": 63190, |
|
"is_parallel": true, |
|
"self": 23.133726682954148 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1085.2138783109976, |
|
"count": 63190, |
|
"is_parallel": true, |
|
"self": 1085.2138783109976 |
|
}, |
|
"steps_from_proto": { |
|
"total": 105.03972721311811, |
|
"count": 63190, |
|
"is_parallel": true, |
|
"self": 19.831815649127748, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 85.20791156399036, |
|
"count": 505520, |
|
"is_parallel": true, |
|
"self": 85.20791156399036 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 633.074333743004, |
|
"count": 63191, |
|
"self": 2.296263444010492, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 105.96893978599837, |
|
"count": 63191, |
|
"self": 105.70650721399852, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.26243257199985237, |
|
"count": 2, |
|
"self": 0.26243257199985237 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 524.8091305129951, |
|
"count": 441, |
|
"self": 336.94047409405675, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 187.86865641893837, |
|
"count": 22794, |
|
"self": 187.86865641893837 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.239994713221677e-07, |
|
"count": 1, |
|
"self": 8.239994713221677e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09572707499955868, |
|
"count": 1, |
|
"self": 0.0014443489999393933, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09428272599961929, |
|
"count": 1, |
|
"self": 0.09428272599961929 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |