{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43201926350593567, "min": 0.4126507341861725, "max": 1.46349036693573, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12953.666015625, "min": 12287.087890625, "max": 44396.4453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2705666422843933, "min": -0.10222095251083374, "max": 0.3841298222541809, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 71.15902709960938, "min": -24.635250091552734, "max": 102.79904174804688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0276415403932333, "min": -0.01512638758867979, "max": 0.34357523918151855, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.269725322723389, "min": -3.96311354637146, "max": 81.42733001708984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06657631831504184, "min": 0.0649188039604471, "max": 0.07286806072030835, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9320684564105857, "min": 0.48991791259607126, "max": 1.0930209108046254, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015950000248440552, "min": 9.515976203027199e-05, "max": 0.015950000248440552, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22330000347816772, "min": 0.0011419171443632639, "max": 0.22330000347816772, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.77211169504286e-06, "min": 7.77211169504286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010880956373060002, "min": 0.00010880956373060002, "max": 0.0031171897609368, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10259067142857141, "min": 0.10259067142857141, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362693999999998, "min": 1.3691136000000002, "max": 2.358575, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026880807571428585, "min": 0.00026880807571428585, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003763313060000002, "min": 0.003763313060000002, "max": 0.10392241368, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010256324894726276, "min": 0.010149536654353142, "max": 0.38958531618118286, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14358854293823242, "min": 0.1420935094356537, "max": 2.727097272872925, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 502.33846153846156, "min": 434.5072463768116, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32652.0, "min": 15984.0, "max": 34641.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.056093732593581, "min": -1.0000000521540642, "max": 1.4205217222156732, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 67.58999888598919, "min": -32.000001668930054, "max": 98.01599883288145, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.056093732593581, "min": -1.0000000521540642, "max": 1.4205217222156732, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 67.58999888598919, "min": -32.000001668930054, "max": 98.01599883288145, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05354071552892492, "min": 0.051713275283649295, "max": 7.448008037172258, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.426605793851195, "min": 2.803995841415599, "max": 119.16812859475613, "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": "1761816776", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1761818871" }, "total": 2095.172577696, "count": 1, "self": 0.44956779399944935, "children": { "run_training.setup": { "total": 0.02278980400024011, "count": 1, "self": 0.02278980400024011 }, "TrainerController.start_learning": { "total": 2094.7002200980005, "count": 1, "self": 1.2415438439129503, "children": { "TrainerController._reset_env": { "total": 2.0502595589996417, "count": 1, "self": 2.0502595589996417 }, "TrainerController.advance": { "total": 2091.3343389500887, "count": 63449, "self": 1.2972198623238, "children": { "env_step": { "total": 1453.6420969577448, "count": 63449, "self": 1311.2657770058504, "children": { "SubprocessEnvManager._take_step": { "total": 141.64597818002858, "count": 63449, "self": 4.430292254113738, "children": { "TorchPolicy.evaluate": { "total": 137.21568592591484, "count": 62561, "self": 137.21568592591484 } } }, "workers": { "total": 0.7303417718658238, "count": 63449, "self": 0.0, "children": { "worker_root": { "total": 2087.979813080963, "count": 63449, "is_parallel": true, "self": 887.6161081809878, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021586829998341273, "count": 1, "is_parallel": true, "self": 0.0006511580004371353, "children": { "_process_rank_one_or_two_observation": { "total": 0.001507524999396992, "count": 8, "is_parallel": true, "self": 0.001507524999396992 } } }, "UnityEnvironment.step": { "total": 0.0501952340000571, "count": 1, "is_parallel": true, "self": 0.0005296079998515779, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000510750000103144, "count": 1, "is_parallel": true, "self": 0.000510750000103144 }, "communicator.exchange": { "total": 0.047508003000075405, "count": 1, "is_parallel": true, "self": 0.047508003000075405 }, "steps_from_proto": { "total": 0.0016468730000269716, "count": 1, "is_parallel": true, "self": 0.00034802899881469784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012988440012122737, "count": 8, "is_parallel": true, "self": 0.0012988440012122737 } } } } } } }, "UnityEnvironment.step": { "total": 1200.3637048999753, "count": 63448, "is_parallel": true, "self": 32.34217209886356, "children": { "UnityEnvironment._generate_step_input": { "total": 22.56324245111682, "count": 63448, "is_parallel": true, "self": 22.56324245111682 }, "communicator.exchange": { "total": 1041.4033060839265, "count": 63448, "is_parallel": true, "self": 1041.4033060839265 }, "steps_from_proto": { "total": 104.05498426606846, "count": 63448, "is_parallel": true, "self": 21.133946034768996, "children": { "_process_rank_one_or_two_observation": { "total": 82.92103823129946, "count": 507584, "is_parallel": true, "self": 82.92103823129946 } } } } } } } } } } }, "trainer_advance": { "total": 636.3950221300202, "count": 63449, "self": 2.2017558661127623, "children": { "process_trajectory": { "total": 118.60743757891669, "count": 63449, "self": 118.42981235591651, "children": { "RLTrainer._checkpoint": { "total": 0.17762522300017736, "count": 2, "self": 0.17762522300017736 } } }, "_update_policy": { "total": 515.5858286849907, "count": 437, "self": 286.60466157509927, "children": { "TorchPPOOptimizer.update": { "total": 228.98116710989143, "count": 22797, "self": 228.98116710989143 } } } } } } }, "trainer_threads": { "total": 1.0969997674692422e-06, "count": 1, "self": 1.0969997674692422e-06 }, "TrainerController._save_models": { "total": 0.07407664799939084, "count": 1, "self": 0.001014790999761317, "children": { "RLTrainer._checkpoint": { "total": 0.07306185699962953, "count": 1, "self": 0.07306185699962953 } } } } } } }