{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3895834684371948, "min": 0.38665997982025146, "max": 1.4985476732254028, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11637.6376953125, "min": 11618.359375, "max": 45459.94140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989934.0, "min": 29952.0, "max": 989934.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989934.0, "min": 29952.0, "max": 989934.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5545145869255066, "min": -0.12184955179691315, "max": 0.6244444251060486, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 154.15505981445312, "min": -29.487590789794922, "max": 176.09332275390625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.028289632871747017, "min": -0.03321745619177818, "max": 0.4802001416683197, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -7.864518165588379, "min": -8.702973365783691, "max": 113.80743408203125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06475563308583436, "min": 0.06475563308583436, "max": 0.07286214358752774, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9065788632016811, "min": 0.48650724241602367, "max": 1.0892353226577944, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016310246625353637, "min": 0.0009794864218074224, "max": 0.0186099435294858, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22834345275495094, "min": 0.01273332348349649, "max": 0.2605392094128012, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.466390368378572e-06, "min": 7.466390368378572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010452946515730001, "min": 0.00010452946515730001, "max": 0.0031369034543656006, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024887642857143, "min": 0.1024887642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348427000000001, "min": 1.3691136000000002, "max": 2.5278557, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002586275521428572, "min": 0.0002586275521428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003620785730000001, "min": 0.003620785730000001, "max": 0.10458887656, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009599106386303902, "min": 0.009599106386303902, "max": 0.5633339285850525, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13438749313354492, "min": 0.13438749313354492, "max": 3.9433374404907227, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 335.65909090909093, "min": 315.57608695652175, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29538.0, "min": 15984.0, "max": 32990.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5984044792444518, "min": -1.0000000521540642, "max": 1.6855824026432666, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 142.2579986527562, "min": -32.000001668930054, "max": 155.49099857360125, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5984044792444518, "min": -1.0000000521540642, "max": 1.6855824026432666, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 142.2579986527562, "min": -32.000001668930054, "max": 155.49099857360125, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03305006304901653, "min": 0.03305006304901653, "max": 12.086440446786582, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9414556113624712, "min": 2.9414556113624712, "max": 193.38304714858532, "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": "1792474043", "python_version": "3.10.22 (main, Oct 9 2026, 15:21:30) [Clang 22.1.3 ]", "command_line_arguments": "/content/ml/bin/mlagents-learn ./PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --force", "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": "1792476679" }, "total": 2635.637561441, "count": 1, "self": 0.8973681319998832, "children": { "run_training.setup": { "total": 0.031239977000041108, "count": 1, "self": 0.031239977000041108 }, "TrainerController.start_learning": { "total": 2634.708953332, "count": 1, "self": 2.281329232990629, "children": { "TrainerController._reset_env": { "total": 1.9816564390000622, "count": 1, "self": 1.9816564390000622 }, "TrainerController.advance": { "total": 2630.379943765009, "count": 63734, "self": 2.1290285441618835, "children": { "env_step": { "total": 1835.0263566929352, "count": 63734, "self": 1690.0149093590153, "children": { "SubprocessEnvManager._take_step": { "total": 143.56674752093477, "count": 63734, "self": 5.47522777392237, "children": { "TorchPolicy.evaluate": { "total": 138.0915197470124, "count": 62539, "self": 138.0915197470124 } } }, "workers": { "total": 1.4446998129851636, "count": 63734, "self": 0.0, "children": { "worker_root": { "total": 2627.97826133599, "count": 63734, "is_parallel": true, "self": 1096.8702908710286, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013119000000187953, "count": 1, "is_parallel": true, "self": 0.00040289999969900236, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009090000003197929, "count": 8, "is_parallel": true, "self": 0.0009090000003197929 } } }, "UnityEnvironment.step": { "total": 0.057651776000057, "count": 1, "is_parallel": true, "self": 0.0005419100002654886, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048001999994085054, "count": 1, "is_parallel": true, "self": 0.00048001999994085054 }, "communicator.exchange": { "total": 0.05493114599994442, "count": 1, "is_parallel": true, "self": 0.05493114599994442 }, "steps_from_proto": { "total": 0.001698699999906239, "count": 1, "is_parallel": true, "self": 0.0003520699999626231, "children": { "_process_rank_one_or_two_observation": { "total": 0.001346629999943616, "count": 8, "is_parallel": true, "self": 0.001346629999943616 } } } } } } }, "UnityEnvironment.step": { "total": 1531.1079704649612, "count": 63733, "is_parallel": true, "self": 37.55031694895706, "children": { "UnityEnvironment._generate_step_input": { "total": 27.397088652036246, "count": 63733, "is_parallel": true, "self": 27.397088652036246 }, "communicator.exchange": { "total": 1357.1181917300667, "count": 63733, "is_parallel": true, "self": 1357.1181917300667 }, "steps_from_proto": { "total": 109.04237313390126, "count": 63733, "is_parallel": true, "self": 25.217013979940248, "children": { "_process_rank_one_or_two_observation": { "total": 83.82535915396102, "count": 509864, "is_parallel": true, "self": 83.82535915396102 } } } } } } } } } } }, "trainer_advance": { "total": 793.224558527912, "count": 63734, "self": 4.455086220900512, "children": { "process_trajectory": { "total": 129.55318913401402, "count": 63734, "self": 129.4080300260141, "children": { "RLTrainer._checkpoint": { "total": 0.14515910799991616, "count": 2, "self": 0.14515910799991616 } } }, "_update_policy": { "total": 659.2162831729975, "count": 443, "self": 255.8344544889651, "children": { "TorchPPOOptimizer.update": { "total": 403.38182868403237, "count": 22839, "self": 403.38182868403237 } } } } } } }, "trainer_threads": { "total": 9.600007615517825e-07, "count": 1, "self": 9.600007615517825e-07 }, "TrainerController._save_models": { "total": 0.06602293499963707, "count": 1, "self": 0.0023281989988390706, "children": { "RLTrainer._checkpoint": { "total": 0.063694736000798, "count": 1, "self": 0.063694736000798 } } } } } } }