|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.14909592270851135, |
|
"min": 0.142119362950325, |
|
"max": 1.3751806020736694, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 4468.1064453125, |
|
"min": 4267.04931640625, |
|
"max": 41717.48046875, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999985.0, |
|
"min": 29952.0, |
|
"max": 2999985.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999985.0, |
|
"min": 29952.0, |
|
"max": 2999985.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7961055040359497, |
|
"min": -0.05584091693162918, |
|
"max": 0.9489213824272156, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 238.03555297851562, |
|
"min": -13.51350212097168, |
|
"max": 299.8591613769531, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.007581324782222509, |
|
"min": -0.04869057983160019, |
|
"max": 0.5447742938995361, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 2.2668161392211914, |
|
"min": -13.828125, |
|
"max": 129.11151123046875, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06762961348932651, |
|
"min": 0.06311524328781863, |
|
"max": 0.07364776081554604, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0144442023398976, |
|
"min": 0.49844704683530194, |
|
"max": 1.1001059048964332, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015988681381956363, |
|
"min": 0.0011898969587066316, |
|
"max": 0.018554184833559122, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23983022072934543, |
|
"min": 0.010709072628359686, |
|
"max": 0.25975858766982773, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.473479508873333e-06, |
|
"min": 1.473479508873333e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.2102192633099995e-05, |
|
"min": 2.2102192633099995e-05, |
|
"max": 0.004052979249006933, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10049112666666665, |
|
"min": 0.10049112666666665, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5073668999999998, |
|
"min": 1.3962282666666668, |
|
"max": 2.827447566666667, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 5.9063553999999996e-05, |
|
"min": 5.9063553999999996e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008859533099999999, |
|
"min": 0.0008859533099999999, |
|
"max": 0.13510420736, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.0069979471154510975, |
|
"min": 0.0069979471154510975, |
|
"max": 0.4304795563220978, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.10496920347213745, |
|
"min": 0.09808759391307831, |
|
"max": 3.013356924057007, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 227.1578947368421, |
|
"min": 200.19736842105263, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30212.0, |
|
"min": 15984.0, |
|
"max": 33949.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7427593881922556, |
|
"min": -1.0000000521540642, |
|
"max": 1.7998026256498538, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 231.78699862957, |
|
"min": -29.47000178694725, |
|
"max": 273.56999909877777, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7427593881922556, |
|
"min": -1.0000000521540642, |
|
"max": 1.7998026256498538, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 231.78699862957, |
|
"min": -29.47000178694725, |
|
"max": 273.56999909877777, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.01641664565479579, |
|
"min": 0.015668555812630477, |
|
"max": 9.890646627172828, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.18341387208784, |
|
"min": 2.0968430308421375, |
|
"max": 158.25034603476524, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1657374594", |
|
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1657381432" |
|
}, |
|
"total": 6838.168301733001, |
|
"count": 1, |
|
"self": 0.43616340900098294, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04169457400007559, |
|
"count": 1, |
|
"self": 0.04169457400007559 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 6837.69044375, |
|
"count": 1, |
|
"self": 4.2923572859044725, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.84102506499994, |
|
"count": 1, |
|
"self": 9.84102506499994 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 6823.463736410095, |
|
"count": 196272, |
|
"self": 4.565868229988155, |
|
"children": { |
|
"env_step": { |
|
"total": 4687.895862876252, |
|
"count": 196272, |
|
"self": 4372.063818228361, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 313.50325280693653, |
|
"count": 196272, |
|
"self": 13.913530251997372, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 299.58972255493916, |
|
"count": 187563, |
|
"self": 102.96363168891742, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 196.62609086602174, |
|
"count": 187563, |
|
"self": 196.62609086602174 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.328791840954864, |
|
"count": 196272, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 6826.345765419902, |
|
"count": 196272, |
|
"is_parallel": true, |
|
"self": 2756.995291435059, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.010451624999973319, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004726090999952248, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.005725534000021071, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.005725534000021071 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04666723100001491, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005056300000205738, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00043689999995422113, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00043689999995422113 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04403368800001317, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04403368800001317 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016910130000269419, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004470860000083121, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012439270000186298, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012439270000186298 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4069.350473984843, |
|
"count": 196271, |
|
"is_parallel": true, |
|
"self": 83.9351488638049, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 68.94728767600509, |
|
"count": 196271, |
|
"is_parallel": true, |
|
"self": 68.94728767600509 |
|
}, |
|
"communicator.exchange": { |
|
"total": 3637.787480832894, |
|
"count": 196271, |
|
"is_parallel": true, |
|
"self": 3637.787480832894 |
|
}, |
|
"steps_from_proto": { |
|
"total": 278.6805566121395, |
|
"count": 196271, |
|
"is_parallel": true, |
|
"self": 69.70327419935177, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 208.97728241278776, |
|
"count": 1570168, |
|
"is_parallel": true, |
|
"self": 208.97728241278776 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2131.0020053038547, |
|
"count": 196272, |
|
"self": 8.439120837779683, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 497.3240388450703, |
|
"count": 196272, |
|
"self": 496.74783120906966, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.5762076360006176, |
|
"count": 6, |
|
"self": 0.5762076360006176 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1625.2388456210047, |
|
"count": 1404, |
|
"self": 647.7126751840763, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 977.5261704369284, |
|
"count": 68343, |
|
"self": 977.5261704369284 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.4979996194597334e-06, |
|
"count": 1, |
|
"self": 1.4979996194597334e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09332349099986459, |
|
"count": 1, |
|
"self": 0.001563761999932467, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09175972899993212, |
|
"count": 1, |
|
"self": 0.09175972899993212 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |