{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5844570994377136, "min": 0.5844570994377136, "max": 1.4705336093902588, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17673.982421875, "min": 17673.982421875, "max": 44610.109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989969.0, "min": 29929.0, "max": 989969.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989969.0, "min": 29929.0, "max": 989969.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2873862087726593, "min": -0.0957401692867279, "max": 0.41016992926597595, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 75.00779724121094, "min": -22.97764015197754, "max": 106.64418029785156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026441605761647224, "min": -0.01817336119711399, "max": 0.2659744620323181, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.901258945465088, "min": -4.688727378845215, "max": 63.03594970703125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06799900894596553, "min": 0.06306030488909624, "max": 0.07406783902317192, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9519861252435173, "min": 0.5153006524118212, "max": 1.0511653672438115, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011921644179632752, "min": 0.0006183629972649539, "max": 0.013319033394162988, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16690301851485853, "min": 0.008038718964444401, "max": 0.18646646751828183, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.2237547349714304e-06, "min": 7.2237547349714304e-06, "max": 0.0002952339015887, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010113256628960003, "min": 0.00010113256628960003, "max": 0.0035073710308764, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10240788571428572, "min": 0.10240788571428572, "max": 0.1984113, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4337104, "min": 1.3888791, "max": 2.5691236, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025054778285714293, "min": 0.00025054778285714293, "max": 0.009841288870000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003507668960000001, "min": 0.003507668960000001, "max": 0.11693544764, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009715327061712742, "min": 0.009715327061712742, "max": 0.3817727267742157, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13601458072662354, "min": 0.13601458072662354, "max": 2.6724090576171875, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 558.1296296296297, "min": 478.5483870967742, "max": 993.0625, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30139.0, "min": 16600.0, "max": 32709.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0840072444894098, "min": -0.9315333872130422, "max": 1.3601354579291036, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 59.620398446917534, "min": -30.740601778030396, "max": 84.32839839160442, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0840072444894098, "min": -0.9315333872130422, "max": 1.3601354579291036, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 59.620398446917534, "min": -30.740601778030396, "max": 84.32839839160442, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.055921556495807385, "min": 0.05042801037592243, "max": 7.48823423946605, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0756856072694063, "min": 3.023637132253498, "max": 127.29998207092285, "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": "1708080234", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1708082694" }, "total": 2459.2538749960004, "count": 1, "self": 1.0603688880000846, "children": { "run_training.setup": { "total": 0.014410777999728452, "count": 1, "self": 0.014410777999728452 }, "TrainerController.start_learning": { "total": 2458.1790953300006, "count": 1, "self": 1.040744421981799, "children": { "TrainerController._reset_env": { "total": 1.32813319300476, "count": 1, "self": 1.32813319300476 }, "TrainerController.advance": { "total": 2455.7478827430095, "count": 63319, "self": 1.0425696274687652, "children": { "env_step": { "total": 971.0401206392926, "count": 63319, "self": 748.7054922495445, "children": { "SubprocessEnvManager._take_step": { "total": 221.62069311880623, "count": 63319, "self": 3.3297559288403136, "children": { "TorchPolicy.evaluate": { "total": 218.29093718996592, "count": 62554, "self": 218.29093718996592 } } }, "workers": { "total": 0.7139352709418745, "count": 63319, "self": 0.0, "children": { "worker_root": { "total": 2455.9311263301497, "count": 63319, "is_parallel": true, "self": 1774.114949582341, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001110568002332002, "count": 1, "is_parallel": true, "self": 0.00036777998320758343, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007427880191244185, "count": 8, "is_parallel": true, "self": 0.0007427880191244185 } } }, "UnityEnvironment.step": { "total": 0.0243381859982037, "count": 1, "is_parallel": true, "self": 0.00016909700207179412, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018770399765344337, "count": 1, "is_parallel": true, "self": 0.00018770399765344337 }, "communicator.exchange": { "total": 0.023462864999601152, "count": 1, "is_parallel": true, "self": 0.023462864999601152 }, "steps_from_proto": { "total": 0.0005185199988773093, "count": 1, "is_parallel": true, "self": 0.000125753998872824, "children": { "_process_rank_one_or_two_observation": { "total": 0.00039276600000448525, "count": 8, "is_parallel": true, "self": 0.00039276600000448525 } } } } } } }, "UnityEnvironment.step": { "total": 681.8161767478086, "count": 63318, "is_parallel": true, "self": 10.854081288525776, "children": { "UnityEnvironment._generate_step_input": { "total": 7.804319265946106, "count": 63318, "is_parallel": true, "self": 7.804319265946106 }, "communicator.exchange": { "total": 631.3118831332831, "count": 63318, "is_parallel": true, "self": 631.3118831332831 }, "steps_from_proto": { "total": 31.84589306005364, "count": 63318, "is_parallel": true, "self": 7.573745271729422, "children": { "_process_rank_one_or_two_observation": { "total": 24.27214778832422, "count": 506544, "is_parallel": true, "self": 24.27214778832422 } } } } } } } } } } }, "trainer_advance": { "total": 1483.6651924762482, "count": 63319, "self": 2.07396284960123, "children": { "process_trajectory": { "total": 121.24039231865027, "count": 63319, "self": 120.9476704016488, "children": { "RLTrainer._checkpoint": { "total": 0.2927219170014723, "count": 2, "self": 0.2927219170014723 } } }, "_update_policy": { "total": 1360.3508373079967, "count": 448, "self": 423.8008196387527, "children": { "TorchPPOOptimizer.update": { "total": 936.550017669244, "count": 22779, "self": 936.550017669244 } } } } } } }, "trainer_threads": { "total": 5.940019036643207e-07, "count": 1, "self": 5.940019036643207e-07 }, "TrainerController._save_models": { "total": 0.0623343780025607, "count": 1, "self": 0.0015039110003272071, "children": { "RLTrainer._checkpoint": { "total": 0.06083046700223349, "count": 1, "self": 0.06083046700223349 } } } } } } }