{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14274290204048157, "min": 0.1400885283946991, "max": 1.4381762742996216, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4232.04150390625, "min": 4200.41455078125, "max": 43628.515625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999943.0, "min": 29952.0, "max": 2999943.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999943.0, "min": 29952.0, "max": 2999943.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7661646604537964, "min": -0.1306808739900589, "max": 0.9027830958366394, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 222.18775939941406, "min": -30.97136878967285, "max": 272.6405029296875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.018598448485136032, "min": -0.0064407638274133205, "max": 0.5080781579017639, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.393549919128418, "min": -1.867821455001831, "max": 120.41452026367188, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06921964839080622, "min": 0.06456119794295066, "max": 0.073816837427837, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.969075077471287, "min": 0.5085131924558597, "max": 1.0738666915179542, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01288479595555642, "min": 0.0006376268148680634, "max": 0.016289365808026764, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18038714337778988, "min": 0.008289148593284824, "max": 0.24434048712040146, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5567423382619082e-06, "min": 1.5567423382619082e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1794392735666716e-05, "min": 2.1794392735666716e-05, "max": 0.0041173670275443655, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051888095238097, "min": 0.10051888095238097, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4072643333333337, "min": 1.3962282666666668, "max": 2.8724556333333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.183620714285727e-05, "min": 6.183620714285727e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008657069000000018, "min": 0.0008657069000000018, "max": 0.13725831777, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006470296997576952, "min": 0.006384584587067366, "max": 0.5330579876899719, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0905841588973999, "min": 0.08938418328762054, "max": 3.7314059734344482, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 238.624, "min": 207.54225352112675, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29828.0, "min": 15984.0, "max": 32862.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7133615875840187, "min": -1.0000000521540642, "max": 1.7912214125905719, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 214.17019844800234, "min": -30.369201704859734, "max": 255.76799814403057, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7133615875840187, "min": -1.0000000521540642, "max": 1.7912214125905719, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 214.17019844800234, "min": -30.369201704859734, "max": 255.76799814403057, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.016131126304913777, "min": 0.014041643471843428, "max": 12.411121679469943, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0163907881142222, "min": 1.937746799114393, "max": 198.5779468715191, "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": "1765731620", "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": "1765739089" }, "total": 7468.946267567, "count": 1, "self": 0.46490740700028255, "children": { "run_training.setup": { "total": 0.02324181999983921, "count": 1, "self": 0.02324181999983921 }, "TrainerController.start_learning": { "total": 7468.4581183400005, "count": 1, "self": 4.5424503695903695, "children": { "TrainerController._reset_env": { "total": 2.133333829000094, "count": 1, "self": 2.133333829000094 }, "TrainerController.advance": { "total": 7461.7061809874085, "count": 195532, "self": 4.5259385993731485, "children": { "env_step": { "total": 5445.430207719206, "count": 195532, "self": 4983.937026356094, "children": { "SubprocessEnvManager._take_step": { "total": 458.7629061873022, "count": 195532, "self": 14.206423121025637, "children": { "TorchPolicy.evaluate": { "total": 444.55648306627654, "count": 187546, "self": 444.55648306627654 } } }, "workers": { "total": 2.7302751758097656, "count": 195532, "self": 0.0, "children": { "worker_root": { "total": 7448.365369912906, "count": 195532, "is_parallel": true, "self": 2829.2585284005963, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002758853999694111, "count": 1, "is_parallel": true, "self": 0.0008029660007196071, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019558879989745037, "count": 8, "is_parallel": true, "self": 0.0019558879989745037 } } }, "UnityEnvironment.step": { "total": 0.055401129000074434, "count": 1, "is_parallel": true, "self": 0.0005702510002265626, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005441789999167668, "count": 1, "is_parallel": true, "self": 0.0005441789999167668 }, "communicator.exchange": { "total": 0.0525886319996971, "count": 1, "is_parallel": true, "self": 0.0525886319996971 }, "steps_from_proto": { "total": 0.0016980670002340048, "count": 1, "is_parallel": true, "self": 0.00037161000045671244, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013264569997772924, "count": 8, "is_parallel": true, "self": 0.0013264569997772924 } } } } } } }, "UnityEnvironment.step": { "total": 4619.10684151231, "count": 195531, "is_parallel": true, "self": 103.07891526709591, "children": { "UnityEnvironment._generate_step_input": { "total": 68.12664852603984, "count": 195531, "is_parallel": true, "self": 68.12664852603984 }, "communicator.exchange": { "total": 4129.806436986028, "count": 195531, "is_parallel": true, "self": 4129.806436986028 }, "steps_from_proto": { "total": 318.09484073314616, "count": 195531, "is_parallel": true, "self": 67.98263217252634, "children": { "_process_rank_one_or_two_observation": { "total": 250.11220856061982, "count": 1564248, "is_parallel": true, "self": 250.11220856061982 } } } } } } } } } } }, "trainer_advance": { "total": 2011.7500346688294, "count": 195532, "self": 9.43141175385972, "children": { "process_trajectory": { "total": 386.2615405150045, "count": 195532, "self": 385.7353017810028, "children": { "RLTrainer._checkpoint": { "total": 0.5262387340017085, "count": 6, "self": 0.5262387340017085 } } }, "_update_policy": { "total": 1616.057082399965, "count": 1403, "self": 895.8630988569594, "children": { "TorchPPOOptimizer.update": { "total": 720.1939835430057, "count": 68361, "self": 720.1939835430057 } } } } } } }, "trainer_threads": { "total": 8.620008884463459e-07, "count": 1, "self": 8.620008884463459e-07 }, "TrainerController._save_models": { "total": 0.07615229200018803, "count": 1, "self": 0.0009459150005568517, "children": { "RLTrainer._checkpoint": { "total": 0.07520637699963117, "count": 1, "self": 0.07520637699963117 } } } } } } }