|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.35345327854156494, |
|
"min": 0.34527915716171265, |
|
"max": 1.37351393699646, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 10552.701171875, |
|
"min": 10391.521484375, |
|
"max": 41666.91796875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989947.0, |
|
"min": 29952.0, |
|
"max": 989947.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989947.0, |
|
"min": 29952.0, |
|
"max": 989947.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6230379343032837, |
|
"min": -0.08095154911279678, |
|
"max": 0.6320415735244751, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 180.05796813964844, |
|
"min": -19.509323120117188, |
|
"max": 180.05796813964844, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.012883156538009644, |
|
"min": -0.04017603024840355, |
|
"max": 0.40541961789131165, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -3.7232322692871094, |
|
"min": -11.249288558959961, |
|
"max": 96.0844497680664, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07011450327860605, |
|
"min": 0.06582186505935776, |
|
"max": 0.07327875021239873, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9816030459004846, |
|
"min": 0.4955172820562689, |
|
"max": 1.046522775858951, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.018326934108674312, |
|
"min": 0.0008007669995927733, |
|
"max": 0.018867222104134027, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2565770775214404, |
|
"min": 0.00960920399511328, |
|
"max": 0.2641411094578764, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.656890304878571e-06, |
|
"min": 7.656890304878571e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010719646426829999, |
|
"min": 0.00010719646426829999, |
|
"max": 0.0034912651362449996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10255226428571428, |
|
"min": 0.10255226428571428, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4357316999999998, |
|
"min": 1.3886848, |
|
"max": 2.4637550000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002649712021428571, |
|
"min": 0.0002649712021428571, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003709596829999999, |
|
"min": 0.003709596829999999, |
|
"max": 0.11638912450000002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.00931136216968298, |
|
"min": 0.009290746413171291, |
|
"max": 0.5060831308364868, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.13035906851291656, |
|
"min": 0.13007044792175293, |
|
"max": 3.5425820350646973, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 294.48623853211006, |
|
"min": 294.48623853211006, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 32099.0, |
|
"min": 15984.0, |
|
"max": 33948.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6137412595776244, |
|
"min": -1.0000000521540642, |
|
"max": 1.6831719844043256, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 175.89779729396105, |
|
"min": -29.869401685893536, |
|
"max": 175.89779729396105, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6137412595776244, |
|
"min": -1.0000000521540642, |
|
"max": 1.6831719844043256, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 175.89779729396105, |
|
"min": -29.869401685893536, |
|
"max": 175.89779729396105, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.028496958238474274, |
|
"min": 0.028496958238474274, |
|
"max": 10.45801231637597, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.1061684479936957, |
|
"min": 2.821122787485365, |
|
"max": 167.32819706201553, |
|
"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": "1678069290", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.22.4", |
|
"end_time_seconds": "1678071732" |
|
}, |
|
"total": 2441.7987226910004, |
|
"count": 1, |
|
"self": 0.44395783800064237, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11221723400012706, |
|
"count": 1, |
|
"self": 0.11221723400012706 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2441.2425476189997, |
|
"count": 1, |
|
"self": 1.6696007180371453, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.430344627000068, |
|
"count": 1, |
|
"self": 6.430344627000068 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2433.055109970962, |
|
"count": 64101, |
|
"self": 1.8074573208700713, |
|
"children": { |
|
"env_step": { |
|
"total": 1681.649756380108, |
|
"count": 64101, |
|
"self": 1549.5265809462744, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 131.06380737895734, |
|
"count": 64101, |
|
"self": 5.204551566841928, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 125.8592558121154, |
|
"count": 62559, |
|
"self": 42.5412634381164, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 83.317992373999, |
|
"count": 62559, |
|
"self": 83.317992373999 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.0593680548763587, |
|
"count": 64101, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2435.3785079899535, |
|
"count": 64101, |
|
"is_parallel": true, |
|
"self": 1017.6152673900665, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019485950001580932, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007401889997709077, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012084060003871855, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012084060003871855 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.07808512800011158, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005552630004785897, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005407429998740554, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005407429998740554 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.0753238889997192, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0753238889997192 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016652330000397342, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004228299999340379, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012424030001056963, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012424030001056963 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1417.763240599887, |
|
"count": 64100, |
|
"is_parallel": true, |
|
"self": 32.582934591045614, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 25.24836792099768, |
|
"count": 64100, |
|
"is_parallel": true, |
|
"self": 25.24836792099768 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1257.591453000839, |
|
"count": 64100, |
|
"is_parallel": true, |
|
"self": 1257.591453000839 |
|
}, |
|
"steps_from_proto": { |
|
"total": 102.34048508700471, |
|
"count": 64100, |
|
"is_parallel": true, |
|
"self": 25.66883875498388, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 76.67164633202083, |
|
"count": 512800, |
|
"is_parallel": true, |
|
"self": 76.67164633202083 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 749.5978962699837, |
|
"count": 64101, |
|
"self": 3.236982620874187, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 172.2698701441177, |
|
"count": 64101, |
|
"self": 172.08089515111715, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.18897499300055642, |
|
"count": 2, |
|
"self": 0.18897499300055642 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 574.0910435049918, |
|
"count": 452, |
|
"self": 219.4041977690058, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 354.686845735986, |
|
"count": 22809, |
|
"self": 354.686845735986 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.209999577957205e-07, |
|
"count": 1, |
|
"self": 8.209999577957205e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08749148200058698, |
|
"count": 1, |
|
"self": 0.0018214600004284875, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0856700220001585, |
|
"count": 1, |
|
"self": 0.0856700220001585 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |