{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5454164147377014, "min": 0.46185725927352905, "max": 1.4011391401290894, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16205.412109375, "min": 13781.8203125, "max": 42504.95703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989953.0, "min": 29948.0, "max": 989953.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989953.0, "min": 29948.0, "max": 989953.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.35639849305152893, "min": -0.10199818015098572, "max": 0.3999486267566681, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 94.08920288085938, "min": -24.581562042236328, "max": 107.18623352050781, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.046996526420116425, "min": 0.010660574771463871, "max": 0.44465360045433044, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.407082557678223, "min": 2.782409906387329, "max": 105.38290405273438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0711954901783934, "min": 0.0664213036318282, "max": 0.0735808894380517, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.067932352675901, "min": 0.5763729922583014, "max": 1.067932352675901, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016635025814563654, "min": 0.00020797345204651296, "max": 0.016635025814563654, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24952538721845482, "min": 0.0027036548766046684, "max": 0.24952538721845482, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.547617484159995e-06, "min": 7.547617484159995e-06, "max": 0.00029501385166205, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011321426226239993, "min": 0.00011321426226239993, "max": 0.0036089022970326, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251584, "min": 0.10251584, "max": 0.19833795000000004, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377376, "min": 1.4780804, "max": 2.5277120000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026133241599999977, "min": 0.00026133241599999977, "max": 0.009833961205, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003919986239999997, "min": 0.003919986239999997, "max": 0.12030644326, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02038090117275715, "min": 0.02038090117275715, "max": 0.5803909301757812, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3057135045528412, "min": 0.29261431097984314, "max": 4.64312744140625, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 469.7, "min": 462.546875, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28182.0, "min": 16875.0, "max": 32803.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.436472114725191, "min": -0.9999226329307402, "max": 1.436472114725191, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 87.62479899823666, "min": -30.997601620852947, "max": 91.23999835550785, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.436472114725191, "min": -0.9999226329307402, "max": 1.436472114725191, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 87.62479899823666, "min": -30.997601620852947, "max": 91.23999835550785, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09708753183720725, "min": 0.09708753183720725, "max": 11.988028636750053, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.922339442069642, "min": 5.922339442069642, "max": 203.7964868247509, "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": "1720031198", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1720035347" }, "total": 4148.552032334999, "count": 1, "self": 0.9965227539996704, "children": { "run_training.setup": { "total": 0.10661077400004615, "count": 1, "self": 0.10661077400004615 }, "TrainerController.start_learning": { "total": 4147.448898807, "count": 1, "self": 3.141370354947867, "children": { "TrainerController._reset_env": { "total": 7.055852748000007, "count": 1, "self": 7.055852748000007 }, "TrainerController.advance": { "total": 4137.1499063380525, "count": 63415, "self": 3.3572352160899754, "children": { "env_step": { "total": 2685.775478426918, "count": 63415, "self": 2461.057575517926, "children": { "SubprocessEnvManager._take_step": { "total": 222.73535494494035, "count": 63415, "self": 10.404430914920795, "children": { "TorchPolicy.evaluate": { "total": 212.33092403001956, "count": 62555, "self": 212.33092403001956 } } }, "workers": { "total": 1.9825479640517187, "count": 63415, "self": 0.0, "children": { "worker_root": { "total": 4137.576540987995, "count": 63415, "is_parallel": true, "self": 1910.9402188401182, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008528806999947847, "count": 1, "is_parallel": true, "self": 0.0026022540000667505, "children": { "_process_rank_one_or_two_observation": { "total": 0.005926552999881096, "count": 8, "is_parallel": true, "self": 0.005926552999881096 } } }, "UnityEnvironment.step": { "total": 0.1541041220000352, "count": 1, "is_parallel": true, "self": 0.0008829149999201036, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000582358999963617, "count": 1, "is_parallel": true, "self": 0.000582358999963617 }, "communicator.exchange": { "total": 0.1488150160000714, "count": 1, "is_parallel": true, "self": 0.1488150160000714 }, "steps_from_proto": { "total": 0.003823832000080074, "count": 1, "is_parallel": true, "self": 0.0007005209999988438, "children": { "_process_rank_one_or_two_observation": { "total": 0.0031233110000812303, "count": 8, "is_parallel": true, "self": 0.0031233110000812303 } } } } } } }, "UnityEnvironment.step": { "total": 2226.636322147877, "count": 63414, "is_parallel": true, "self": 58.63561623207306, "children": { "UnityEnvironment._generate_step_input": { "total": 37.38339134793091, "count": 63414, "is_parallel": true, "self": 37.38339134793091 }, "communicator.exchange": { "total": 1958.7770889999867, "count": 63414, "is_parallel": true, "self": 1958.7770889999867 }, "steps_from_proto": { "total": 171.84022556788614, "count": 63414, "is_parallel": true, "self": 38.81469304087818, "children": { "_process_rank_one_or_two_observation": { "total": 133.02553252700795, "count": 507312, "is_parallel": true, "self": 133.02553252700795 } } } } } } } } } } }, "trainer_advance": { "total": 1448.0171926950443, "count": 63415, "self": 6.9310036881354335, "children": { "process_trajectory": { "total": 210.65884664191321, "count": 63415, "self": 210.42352953591285, "children": { "RLTrainer._checkpoint": { "total": 0.23531710600036604, "count": 2, "self": 0.23531710600036604 } } }, "_update_policy": { "total": 1230.4273423649956, "count": 454, "self": 522.6069348470153, "children": { "TorchPPOOptimizer.update": { "total": 707.8204075179804, "count": 22746, "self": 707.8204075179804 } } } } } } }, "trainer_threads": { "total": 1.1610000001383014e-06, "count": 1, "self": 1.1610000001383014e-06 }, "TrainerController._save_models": { "total": 0.10176820499964379, "count": 1, "self": 0.0034229139992021373, "children": { "RLTrainer._checkpoint": { "total": 0.09834529100044165, "count": 1, "self": 0.09834529100044165 } } } } } } }