{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6491014361381531, "min": 0.6491014361381531, "max": 1.4836331605911255, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19441.88671875, "min": 19379.755859375, "max": 45007.49609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.027338389307260513, "min": -0.12243355065584183, "max": 0.1684580147266388, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 6.77992057800293, "min": -29.506484985351562, "max": 41.946044921875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.8278272151947021, "min": -1.0393418073654175, "max": 0.20329788327217102, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -205.3011474609375, "min": -256.7174377441406, "max": 51.027767181396484, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06915984292177442, "min": 0.06467136650911014, "max": 0.07459305319688968, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9682378009048419, "min": 0.5221513723782277, "max": 1.075083551681589, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.4196737280396904, "min": 0.0010237265992074462, "max": 0.5121560453969044, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 5.875432192555666, "min": 0.01267923497004926, "max": 7.170184635556662, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.61904746035e-06, "min": 7.61904746035e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001066666644449, "min": 0.0001066666644449, "max": 0.003380958273014, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253964999999998, "min": 0.10253964999999998, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355550999999998, "min": 1.3886848, "max": 2.5269860000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026371103500000005, "min": 0.00026371103500000005, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003691954490000001, "min": 0.003691954490000001, "max": 0.11272590140000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006467525847256184, "min": 0.00570510933175683, "max": 0.3216618001461029, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09054536372423172, "min": 0.0798715278506279, "max": 2.2516326904296875, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 830.4864864864865, "min": 699.4, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30728.0, "min": 15984.0, "max": 33246.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.020000040732525492, "min": -1.0000000521540642, "max": 0.70040996465832, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -0.7400015071034431, "min": -30.39160170406103, "max": 28.016398586332798, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.020000040732525492, "min": -1.0000000521540642, "max": 0.70040996465832, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -0.7400015071034431, "min": -30.39160170406103, "max": 28.016398586332798, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.057826326320709255, "min": 0.050467297217850995, "max": 5.9205503752455115, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1395740738662425, "min": 1.665420808189083, "max": 94.72880600392818, "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": "1777296934", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [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": "1.2.0.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": "1777300533" }, "total": 3598.0653422299993, "count": 1, "self": 0.7931120980001651, "children": { "run_training.setup": { "total": 0.04114586200012127, "count": 1, "self": 0.04114586200012127 }, "TrainerController.start_learning": { "total": 3597.231084269999, "count": 1, "self": 2.299133543849166, "children": { "TrainerController._reset_env": { "total": 3.02210829500018, "count": 1, "self": 3.02210829500018 }, "TrainerController.advance": { "total": 3591.830499117149, "count": 63336, "self": 2.648936630843309, "children": { "env_step": { "total": 2466.9026596640506, "count": 63336, "self": 2295.9445654822075, "children": { "SubprocessEnvManager._take_step": { "total": 169.44256368790684, "count": 63336, "self": 7.613253815982716, "children": { "TorchPolicy.evaluate": { "total": 161.82930987192412, "count": 62565, "self": 161.82930987192412 } } }, "workers": { "total": 1.5155304939362395, "count": 63336, "self": 0.0, "children": { "worker_root": { "total": 3588.0182854478553, "count": 63336, "is_parallel": true, "self": 1484.094530694836, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003324477000205661, "count": 1, "is_parallel": true, "self": 0.0010955119987556827, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022289650014499784, "count": 8, "is_parallel": true, "self": 0.0022289650014499784 } } }, "UnityEnvironment.step": { "total": 0.07274317200062796, "count": 1, "is_parallel": true, "self": 0.0006960320006328402, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005642080004690797, "count": 1, "is_parallel": true, "self": 0.0005642080004690797 }, "communicator.exchange": { "total": 0.06932123800015688, "count": 1, "is_parallel": true, "self": 0.06932123800015688 }, "steps_from_proto": { "total": 0.002161693999369163, "count": 1, "is_parallel": true, "self": 0.000422744000388775, "children": { "_process_rank_one_or_two_observation": { "total": 0.001738949998980388, "count": 8, "is_parallel": true, "self": 0.001738949998980388 } } } } } } }, "UnityEnvironment.step": { "total": 2103.9237547530192, "count": 63335, "is_parallel": true, "self": 48.18138141005511, "children": { "UnityEnvironment._generate_step_input": { "total": 32.4796606386617, "count": 63335, "is_parallel": true, "self": 32.4796606386617 }, "communicator.exchange": { "total": 1870.2185288470137, "count": 63335, "is_parallel": true, "self": 1870.2185288470137 }, "steps_from_proto": { "total": 153.04418385728877, "count": 63335, "is_parallel": true, "self": 30.419733656250173, "children": { "_process_rank_one_or_two_observation": { "total": 122.6244502010386, "count": 506680, "is_parallel": true, "self": 122.6244502010386 } } } } } } } } } } }, "trainer_advance": { "total": 1122.278902822255, "count": 63336, "self": 4.625631199330201, "children": { "process_trajectory": { "total": 167.05033949391236, "count": 63336, "self": 166.7891697139121, "children": { "RLTrainer._checkpoint": { "total": 0.261169780000273, "count": 2, "self": 0.261169780000273 } } }, "_update_policy": { "total": 950.6029321290125, "count": 447, "self": 374.07206745596795, "children": { "TorchPPOOptimizer.update": { "total": 576.5308646730446, "count": 22773, "self": 576.5308646730446 } } } } } } }, "trainer_threads": { "total": 1.4920005924068391e-06, "count": 1, "self": 1.4920005924068391e-06 }, "TrainerController._save_models": { "total": 0.07934182200006035, "count": 1, "self": 0.002238132999991649, "children": { "RLTrainer._checkpoint": { "total": 0.0771036890000687, "count": 1, "self": 0.0771036890000687 } } } } } } }