|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.6266112327575684, |
|
"min": 0.6195098161697388, |
|
"max": 1.4313980340957642, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 18858.4921875, |
|
"min": 18666.369140625, |
|
"max": 43422.890625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989904.0, |
|
"min": 29952.0, |
|
"max": 989904.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989904.0, |
|
"min": 29952.0, |
|
"max": 989904.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.10021860152482986, |
|
"min": -0.11149105429649353, |
|
"max": 0.16706934571266174, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 24.85421371459961, |
|
"min": -26.42337989807129, |
|
"max": 42.10147476196289, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.005289188586175442, |
|
"min": -0.05889393761754036, |
|
"max": 0.3789993226528168, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 1.3117188215255737, |
|
"min": -14.841272354125977, |
|
"max": 89.82283782958984, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06923651513225144, |
|
"min": 0.06566447798953606, |
|
"max": 0.0724332001237927, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9693112118515201, |
|
"min": 0.4957873256297163, |
|
"max": 1.0519123977539817, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.006032011421623229, |
|
"min": 6.410518252799537e-05, |
|
"max": 0.010225357106202293, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.08444815990272521, |
|
"min": 0.0008333673728639398, |
|
"max": 0.1434543826450619, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.2879332850071435e-06, |
|
"min": 7.2879332850071435e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010203106599010001, |
|
"min": 0.00010203106599010001, |
|
"max": 0.0035084738305087996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10242927857142858, |
|
"min": 0.10242927857142858, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4340099000000002, |
|
"min": 1.3886848, |
|
"max": 2.5694912, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002526849292857144, |
|
"min": 0.0002526849292857144, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003537589010000001, |
|
"min": 0.003537589010000001, |
|
"max": 0.11697217088, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.012031533755362034, |
|
"min": 0.012031533755362034, |
|
"max": 0.4214365482330322, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.16844147443771362, |
|
"min": 0.16844147443771362, |
|
"max": 2.9500558376312256, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 712.8636363636364, |
|
"min": 622.6304347826087, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31366.0, |
|
"min": 15984.0, |
|
"max": 33861.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.28679996203969826, |
|
"min": -1.0000000521540642, |
|
"max": 0.7685086582989796, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 12.619198329746723, |
|
"min": -29.984001711010933, |
|
"max": 35.35139828175306, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.28679996203969826, |
|
"min": -1.0000000521540642, |
|
"max": 0.7685086582989796, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 12.619198329746723, |
|
"min": -29.984001711010933, |
|
"max": 35.35139828175306, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.08704382547842794, |
|
"min": 0.07937806729308289, |
|
"max": 8.651869429275393, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.8299283210508293, |
|
"min": 3.6433891475899145, |
|
"max": 138.4299108684063, |
|
"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": "1685637615", |
|
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685640873" |
|
}, |
|
"total": 3258.687321362, |
|
"count": 1, |
|
"self": 0.8521592490005787, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0678623050000624, |
|
"count": 1, |
|
"self": 0.0678623050000624 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 3257.7672998079997, |
|
"count": 1, |
|
"self": 2.6144310609565764, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 1.0591109530000722, |
|
"count": 1, |
|
"self": 1.0591109530000722 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 3253.979553959043, |
|
"count": 63292, |
|
"self": 2.4429497231753885, |
|
"children": { |
|
"env_step": { |
|
"total": 2078.0698802549414, |
|
"count": 63292, |
|
"self": 1935.141132777964, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 141.38698347103264, |
|
"count": 63292, |
|
"self": 7.0275143119583845, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 134.35946915907425, |
|
"count": 62559, |
|
"self": 134.35946915907425 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.5417640059447422, |
|
"count": 63292, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 3251.0592118920313, |
|
"count": 63292, |
|
"is_parallel": true, |
|
"self": 1492.0053901019685, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.003113027000154034, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0009668839998084877, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002146143000345546, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002146143000345546 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.06381458100008786, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006579739999779122, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00042191500006083515, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00042191500006083515 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.06040365700005168, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.06040365700005168 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.002331034999997428, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00047907599991958705, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0018519590000778408, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0018519590000778408 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1759.0538217900628, |
|
"count": 63291, |
|
"is_parallel": true, |
|
"self": 46.297120909992145, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 25.852240827914102, |
|
"count": 63291, |
|
"is_parallel": true, |
|
"self": 25.852240827914102 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1548.3821290810993, |
|
"count": 63291, |
|
"is_parallel": true, |
|
"self": 1548.3821290810993 |
|
}, |
|
"steps_from_proto": { |
|
"total": 138.52233097105727, |
|
"count": 63291, |
|
"is_parallel": true, |
|
"self": 29.526155669067748, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 108.99617530198952, |
|
"count": 506328, |
|
"is_parallel": true, |
|
"self": 108.99617530198952 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1173.4667239809264, |
|
"count": 63292, |
|
"self": 4.619700237959023, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 147.38542179796468, |
|
"count": 63292, |
|
"self": 147.0363191839656, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.3491026139990936, |
|
"count": 2, |
|
"self": 0.3491026139990936 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1021.4616019450027, |
|
"count": 448, |
|
"self": 425.31837266501, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 596.1432292799927, |
|
"count": 22815, |
|
"self": 596.1432292799927 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.2919999790028669e-06, |
|
"count": 1, |
|
"self": 1.2919999790028669e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.11420254299991939, |
|
"count": 1, |
|
"self": 0.0018042030005744891, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1123983399993449, |
|
"count": 1, |
|
"self": 0.1123983399993449 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |