{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4994644522666931, "min": 0.4735771715641022, "max": 1.4950975179672241, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15103.8046875, "min": 14343.705078125, "max": 45355.27734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989969.0, "min": 29952.0, "max": 989969.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1240638867020607, "min": -0.19752952456474304, "max": 0.16791479289531708, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 31.51222801208496, "min": -46.81449890136719, "max": 42.98618698120117, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.18933457136154175, "min": -0.18933457136154175, "max": 0.2163684368133545, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -48.090980529785156, "min": -48.090980529785156, "max": 51.37353515625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06655651873069898, "min": 0.06439506671266207, "max": 0.07275657839797559, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9317912622297858, "min": 0.497321773732908, "max": 1.0587152248675316, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.028634992584964655, "min": 0.0001616355790895853, "max": 0.028634992584964655, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.40088989618950516, "min": 0.002101262528164609, "max": 0.40088989618950516, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.32706184339286e-06, "min": 7.32706184339286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010257886580750004, "min": 0.00010257886580750004, "max": 0.0036323545892152, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244232142857145, "min": 0.10244232142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341925000000002, "min": 1.3886848, "max": 2.6107848000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025398791071428584, "min": 0.00025398791071428584, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035558307500000016, "min": 0.0035558307500000016, "max": 0.12109740152000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00966096855700016, "min": 0.00966096855700016, "max": 0.3224920928478241, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13525356352329254, "min": 0.13525356352329254, "max": 2.2574446201324463, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 671.1590909090909, "min": 649.2083333333334, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29531.0, "min": 15984.0, "max": 33378.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6922863332385366, "min": -1.0000000521540642, "max": 0.8089624537775914, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 30.460598662495613, "min": -30.52440172433853, "max": 38.83019778132439, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6922863332385366, "min": -1.0000000521540642, "max": 0.8089624537775914, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 30.460598662495613, "min": -30.52440172433853, "max": 38.83019778132439, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06731611068773252, "min": 0.06731611068773252, "max": 6.8133134031668305, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.961908870260231, "min": 2.961908870260231, "max": 109.01301445066929, "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": "1716021452", "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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716023631" }, "total": 2178.887512941, "count": 1, "self": 0.9475279039997986, "children": { "run_training.setup": { "total": 0.050291016000073796, "count": 1, "self": 0.050291016000073796 }, "TrainerController.start_learning": { "total": 2177.8896940209997, "count": 1, "self": 1.4740692520485936, "children": { "TrainerController._reset_env": { "total": 2.0425731450000058, "count": 1, "self": 2.0425731450000058 }, "TrainerController.advance": { "total": 2174.2373763099517, "count": 63308, "self": 1.541985323883182, "children": { "env_step": { "total": 1530.666740577079, "count": 63308, "self": 1388.9623905290548, "children": { "SubprocessEnvManager._take_step": { "total": 140.75256642905788, "count": 63308, "self": 5.057422315047916, "children": { "TorchPolicy.evaluate": { "total": 135.69514411400996, "count": 62556, "self": 135.69514411400996 } } }, "workers": { "total": 0.951783618966374, "count": 63308, "self": 0.0, "children": { "worker_root": { "total": 2172.247273427965, "count": 63308, "is_parallel": true, "self": 916.9302244259341, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002215369999930772, "count": 1, "is_parallel": true, "self": 0.0006615869997403934, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015537830001903785, "count": 8, "is_parallel": true, "self": 0.0015537830001903785 } } }, "UnityEnvironment.step": { "total": 0.05288160099985362, "count": 1, "is_parallel": true, "self": 0.000606324999807839, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005160910000086005, "count": 1, "is_parallel": true, "self": 0.0005160910000086005 }, "communicator.exchange": { "total": 0.0499939409999115, "count": 1, "is_parallel": true, "self": 0.0499939409999115 }, "steps_from_proto": { "total": 0.0017652440001256764, "count": 1, "is_parallel": true, "self": 0.0003643270003976795, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014009169997279969, "count": 8, "is_parallel": true, "self": 0.0014009169997279969 } } } } } } }, "UnityEnvironment.step": { "total": 1255.317049002031, "count": 63307, "is_parallel": true, "self": 35.05742697409801, "children": { "UnityEnvironment._generate_step_input": { "total": 25.411080541940464, "count": 63307, "is_parallel": true, "self": 25.411080541940464 }, "communicator.exchange": { "total": 1089.203069854975, "count": 63307, "is_parallel": true, "self": 1089.203069854975 }, "steps_from_proto": { "total": 105.64547163101747, "count": 63307, "is_parallel": true, "self": 21.875942771988093, "children": { "_process_rank_one_or_two_observation": { "total": 83.76952885902938, "count": 506456, "is_parallel": true, "self": 83.76952885902938 } } } } } } } } } } }, "trainer_advance": { "total": 642.0286504089897, "count": 63308, "self": 2.852812949018926, "children": { "process_trajectory": { "total": 132.76858220197255, "count": 63308, "self": 132.53944290197296, "children": { "RLTrainer._checkpoint": { "total": 0.22913929999958782, "count": 2, "self": 0.22913929999958782 } } }, "_update_policy": { "total": 506.40725525799826, "count": 450, "self": 300.14171079497623, "children": { "TorchPPOOptimizer.update": { "total": 206.26554446302202, "count": 22770, "self": 206.26554446302202 } } } } } } }, "trainer_threads": { "total": 1.1859997357532848e-06, "count": 1, "self": 1.1859997357532848e-06 }, "TrainerController._save_models": { "total": 0.13567412799966405, "count": 1, "self": 0.0023141199994825, "children": { "RLTrainer._checkpoint": { "total": 0.13336000800018155, "count": 1, "self": 0.13336000800018155 } } } } } } }