{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.12908047437667847, "min": 0.12673941254615784, "max": 1.4291459321975708, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3860.022705078125, "min": 3804.210205078125, "max": 43354.5703125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999998.0, "min": 29952.0, "max": 2999998.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999998.0, "min": 29952.0, "max": 2999998.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7986339926719666, "min": -0.07827374339103699, "max": 0.8544501066207886, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 234.79840087890625, "min": -18.863971710205078, "max": 261.46173095703125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007089178543537855, "min": -0.004081136081367731, "max": 0.5816629528999329, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.0842185020446777, "min": -1.1345558166503906, "max": 137.8541259765625, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0686852690033404, "min": 0.06473526618875829, "max": 0.07518472419023683, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9615937660467656, "min": 0.5120259907587374, "max": 1.0938631357760946, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01476910247306694, "min": 0.0006978184901949426, "max": 0.016922780360533473, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20676743462293717, "min": 0.008373821882339311, "max": 0.24052662018705936, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5034494988833267e-06, "min": 1.5034494988833267e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1048292984366574e-05, "min": 2.1048292984366574e-05, "max": 0.004027586357471266, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050111666666668, "min": 0.10050111666666668, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070156333333335, "min": 1.3962282666666668, "max": 2.8425287333333342, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.006155499999978e-05, "min": 6.006155499999978e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.000840861769999997, "min": 0.000840861769999997, "max": 0.13426862046000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00791836716234684, "min": 0.007484130561351776, "max": 0.6162473559379578, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11085714399814606, "min": 0.10477782785892487, "max": 4.313731670379639, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 240.4608695652174, "min": 204.71724137931034, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27653.0, "min": 15984.0, "max": 33541.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7088620578549032, "min": -1.0000000521540642, "max": 1.7814827480706674, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 198.22799871116877, "min": -30.48300166428089, "max": 258.50739800930023, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7088620578549032, "min": -1.0000000521540642, "max": 1.7814827480706674, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 198.22799871116877, "min": -30.48300166428089, "max": 258.50739800930023, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019215105199158453, "min": 0.01650436283530796, "max": 12.46143932454288, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2289522031023807, "min": 2.2289522031023807, "max": 199.38302919268608, "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": "1698271255", "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", "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": "1698277915" }, "total": 6659.906532305, "count": 1, "self": 0.42782697600159736, "children": { "run_training.setup": { "total": 0.07491982500005179, "count": 1, "self": 0.07491982500005179 }, "TrainerController.start_learning": { "total": 6659.403785503999, "count": 1, "self": 5.422188401174026, "children": { "TrainerController._reset_env": { "total": 1.1716168479997577, "count": 1, "self": 1.1716168479997577 }, "TrainerController.advance": { "total": 6652.7578160158255, "count": 195414, "self": 5.031926708782521, "children": { "env_step": { "total": 4606.678506148075, "count": 195414, "self": 4280.609979365012, "children": { "SubprocessEnvManager._take_step": { "total": 322.70466352607264, "count": 195414, "self": 12.185834426377369, "children": { "TorchPolicy.evaluate": { "total": 310.51882909969527, "count": 187558, "self": 310.51882909969527 } } }, "workers": { "total": 3.3638632569904985, "count": 195414, "self": 0.0, "children": { "worker_root": { "total": 6649.100664973836, "count": 195414, "is_parallel": true, "self": 2709.8072729899145, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018982699998559838, "count": 1, "is_parallel": true, "self": 0.0005603819995485537, "children": { "_process_rank_one_or_two_observation": { "total": 0.00133788800030743, "count": 8, "is_parallel": true, "self": 0.00133788800030743 } } }, "UnityEnvironment.step": { "total": 0.044720646000314446, "count": 1, "is_parallel": true, "self": 0.0005046200003562262, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041211999996448867, "count": 1, "is_parallel": true, "self": 0.00041211999996448867 }, "communicator.exchange": { "total": 0.0422388859997227, "count": 1, "is_parallel": true, "self": 0.0422388859997227 }, "steps_from_proto": { "total": 0.0015650200002710335, "count": 1, "is_parallel": true, "self": 0.00032326900100088096, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012417509992701525, "count": 8, "is_parallel": true, "self": 0.0012417509992701525 } } } } } } }, "UnityEnvironment.step": { "total": 3939.293391983921, "count": 195413, "is_parallel": true, "self": 93.2864483037506, "children": { "UnityEnvironment._generate_step_input": { "total": 50.732851782134276, "count": 195413, "is_parallel": true, "self": 50.732851782134276 }, "communicator.exchange": { "total": 3526.191611877836, "count": 195413, "is_parallel": true, "self": 3526.191611877836 }, "steps_from_proto": { "total": 269.08248002020036, "count": 195413, "is_parallel": true, "self": 57.38929644669088, "children": { "_process_rank_one_or_two_observation": { "total": 211.6931835735095, "count": 1563304, "is_parallel": true, "self": 211.6931835735095 } } } } } } } } } } }, "trainer_advance": { "total": 2041.0473831589675, "count": 195414, "self": 10.385957622773276, "children": { "process_trajectory": { "total": 317.1379166681918, "count": 195414, "self": 316.72669591219255, "children": { "RLTrainer._checkpoint": { "total": 0.41122075599923846, "count": 6, "self": 0.41122075599923846 } } }, "_update_policy": { "total": 1713.5235088680024, "count": 1400, "self": 705.1359684688141, "children": { "TorchPPOOptimizer.update": { "total": 1008.3875403991883, "count": 68361, "self": 1008.3875403991883 } } } } } } }, "trainer_threads": { "total": 1.4309989637695253e-06, "count": 1, "self": 1.4309989637695253e-06 }, "TrainerController._save_models": { "total": 0.05216280800050299, "count": 1, "self": 0.0009505200014245929, "children": { "RLTrainer._checkpoint": { "total": 0.0512122879990784, "count": 1, "self": 0.0512122879990784 } } } } } } }