{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3506196141242981, "min": 0.3506196141242981, "max": 1.435718059539795, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10597.126953125, "min": 10597.126953125, "max": 43553.94140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29904.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29904.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5892725586891174, "min": -0.08595546334981918, "max": 0.6756123304367065, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 163.81776428222656, "min": -20.715267181396484, "max": 194.57635498046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.030525920912623405, "min": -0.030525920912623405, "max": 0.32834094762802124, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.4862060546875, "min": -8.4862060546875, "max": 77.81680297851562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06778520575469538, "min": 0.06664934588479811, "max": 0.07466580772528515, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9489928805657353, "min": 0.5589956592803165, "max": 1.0588430338539183, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01667608187834084, "min": 0.0010325357794728812, "max": 0.0175427032673421, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23346514629677176, "min": 0.013422965133147457, "max": 0.2631405490101315, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.561747479450004e-06, "min": 7.561747479450004e-06, "max": 0.00029521470159509997, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010586446471230006, "min": 0.00010586446471230006, "max": 0.0036330592889803, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252055000000002, "min": 0.10252055000000002, "max": 0.1984049, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352877000000002, "min": 1.4352877000000002, "max": 2.6110197000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002618029450000002, "min": 0.0002618029450000002, "max": 0.00984064951, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003665241230000002, "min": 0.003665241230000002, "max": 0.12112086803000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01119464635848999, "min": 0.01119464635848999, "max": 0.39911597967147827, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15672504901885986, "min": 0.15672504901885986, "max": 3.192927837371826, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 321.3936170212766, "min": 276.51960784313724, "max": 996.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30211.0, "min": 15936.0, "max": 34214.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6147616862299594, "min": -0.9288065027325384, "max": 1.723480379902849, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 151.7875985056162, "min": -28.79300158470869, "max": 178.2849980443716, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6147616862299594, "min": -0.9288065027325384, "max": 1.723480379902849, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 151.7875985056162, "min": -28.79300158470869, "max": 178.2849980443716, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03722004433748612, "min": 0.034992316024236775, "max": 7.843625839799643, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4986841677236953, "min": 3.4986841677236953, "max": 125.49801343679428, "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": "1756492948", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]", "command_line_arguments": "/home/sam/.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": "1756494600" }, "total": 1549.8057936100013, "count": 1, "self": 0.47737452200453845, "children": { "run_training.setup": { "total": 0.024550932997954078, "count": 1, "self": 0.024550932997954078 }, "TrainerController.start_learning": { "total": 1549.3038681549988, "count": 1, "self": 1.09274243634718, "children": { "TrainerController._reset_env": { "total": 3.4976133739983197, "count": 1, "self": 3.4976133739983197 }, "TrainerController.advance": { "total": 1544.6385271596519, "count": 64075, "self": 1.1245555171408341, "children": { "env_step": { "total": 1033.4813289601589, "count": 64075, "self": 831.2906537351737, "children": { "SubprocessEnvManager._take_step": { "total": 201.47321315782756, "count": 64075, "self": 3.511273920732492, "children": { "TorchPolicy.evaluate": { "total": 197.96193923709507, "count": 62564, "self": 197.96193923709507 } } }, "workers": { "total": 0.7174620671576122, "count": 64075, "self": 0.0, "children": { "worker_root": { "total": 1546.785181969084, "count": 64075, "is_parallel": true, "self": 782.2920621200174, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018416909988445695, "count": 1, "is_parallel": true, "self": 0.0008840340015012771, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009576569973432925, "count": 8, "is_parallel": true, "self": 0.0009576569973432925 } } }, "UnityEnvironment.step": { "total": 0.03194311499828473, "count": 1, "is_parallel": true, "self": 0.00018232400543638505, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001579729978402611, "count": 1, "is_parallel": true, "self": 0.0001579729978402611 }, "communicator.exchange": { "total": 0.031007185996713815, "count": 1, "is_parallel": true, "self": 0.031007185996713815 }, "steps_from_proto": { "total": 0.0005956319982942659, "count": 1, "is_parallel": true, "self": 0.0001189479953609407, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047668400293332525, "count": 8, "is_parallel": true, "self": 0.00047668400293332525 } } } } } } }, "UnityEnvironment.step": { "total": 764.4931198490667, "count": 64074, "is_parallel": true, "self": 10.974096731555619, "children": { "UnityEnvironment._generate_step_input": { "total": 7.600947237100627, "count": 64074, "is_parallel": true, "self": 7.600947237100627 }, "communicator.exchange": { "total": 717.8180234088468, "count": 64074, "is_parallel": true, "self": 717.8180234088468 }, "steps_from_proto": { "total": 28.100052471563686, "count": 64074, "is_parallel": true, "self": 6.626374352519633, "children": { "_process_rank_one_or_two_observation": { "total": 21.473678119044052, "count": 512592, "is_parallel": true, "self": 21.473678119044052 } } } } } } } } } } }, "trainer_advance": { "total": 510.03264268235216, "count": 64075, "self": 2.034144255801948, "children": { "process_trajectory": { "total": 91.01332291253493, "count": 64075, "self": 90.74448516553457, "children": { "RLTrainer._checkpoint": { "total": 0.26883774700036156, "count": 2, "self": 0.26883774700036156 } } }, "_update_policy": { "total": 416.9851755140153, "count": 460, "self": 180.6812752509759, "children": { "TorchPPOOptimizer.update": { "total": 236.3039002630394, "count": 22818, "self": 236.3039002630394 } } } } } } }, "trainer_threads": { "total": 5.520014383364469e-07, "count": 1, "self": 5.520014383364469e-07 }, "TrainerController._save_models": { "total": 0.07498463299998548, "count": 1, "self": 0.0018816149968188256, "children": { "RLTrainer._checkpoint": { "total": 0.07310301800316665, "count": 1, "self": 0.07310301800316665 } } } } } } }