{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2630590498447418, "min": 0.260686993598938, "max": 1.4080257415771484, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7967.5322265625, "min": 7820.60986328125, "max": 42713.8671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.512125551700592, "min": -0.10252418369054794, "max": 0.5883321762084961, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.3708953857422, "min": -24.708328247070312, "max": 165.3213348388672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00012290092126931995, "min": -0.006286347284913063, "max": 0.2322310507297516, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.03416645526885986, "min": -1.7098864316940308, "max": 55.967681884765625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06906213116391362, "min": 0.06284252128697763, "max": 0.07243062176099654, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9668698362947907, "min": 0.5070143523269758, "max": 1.072647689259611, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015590981529385315, "min": 0.00021146499505555192, "max": 0.015590981529385315, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2182737414113944, "min": 0.002537579940666623, "max": 0.2182737414113944, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.341547552850003e-06, "min": 7.341547552850003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010278166573990005, "min": 0.00010278166573990005, "max": 0.0031372418542527994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244715000000003, "min": 0.10244715000000003, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342601000000004, "min": 1.3886848, "max": 2.4423257, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025447028500000013, "min": 0.00025447028500000013, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035625839900000015, "min": 0.0035625839900000015, "max": 0.10460014527999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010092445649206638, "min": 0.010092445649206638, "max": 0.38658854365348816, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14129424095153809, "min": 0.14129424095153809, "max": 2.7061197757720947, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 368.8139534883721, "min": 331.9583333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31718.0, "min": 15984.0, "max": 33430.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5613906756909781, "min": -1.0000000521540642, "max": 1.6472062339695792, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.27959810942411, "min": -32.000001668930054, "max": 158.1317984610796, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5613906756909781, "min": -1.0000000521540642, "max": 1.6472062339695792, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.27959810942411, "min": -32.000001668930054, "max": 158.1317984610796, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03827912207736179, "min": 0.03659147060676421, "max": 7.76106836181134, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.292004498653114, "min": 3.0005005897546653, "max": 124.17709378898144, "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": "1733017459", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1733020930" }, "total": 3471.067061704, "count": 1, "self": 0.7560304379999252, "children": { "run_training.setup": { "total": 0.07514669899995852, "count": 1, "self": 0.07514669899995852 }, "TrainerController.start_learning": { "total": 3470.235884567, "count": 1, "self": 2.3538947289266616, "children": { "TrainerController._reset_env": { "total": 6.392761468000003, "count": 1, "self": 6.392761468000003 }, "TrainerController.advance": { "total": 3461.3944915120737, "count": 63901, "self": 2.44964012111177, "children": { "env_step": { "total": 2349.9380653939543, "count": 63901, "self": 2182.722877427921, "children": { "SubprocessEnvManager._take_step": { "total": 165.82084231200633, "count": 63901, "self": 7.0678217170002995, "children": { "TorchPolicy.evaluate": { "total": 158.75302059500603, "count": 62554, "self": 158.75302059500603 } } }, "workers": { "total": 1.3943456540268357, "count": 63901, "self": 0.0, "children": { "worker_root": { "total": 3462.597453573025, "count": 63901, "is_parallel": true, "self": 1459.3293124060133, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024202070000001186, "count": 1, "is_parallel": true, "self": 0.0007652370000528208, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016549699999472978, "count": 8, "is_parallel": true, "self": 0.0016549699999472978 } } }, "UnityEnvironment.step": { "total": 0.06004624399997738, "count": 1, "is_parallel": true, "self": 0.0007644180000170309, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000507192999975814, "count": 1, "is_parallel": true, "self": 0.000507192999975814 }, "communicator.exchange": { "total": 0.05679142999997566, "count": 1, "is_parallel": true, "self": 0.05679142999997566 }, "steps_from_proto": { "total": 0.0019832030000088707, "count": 1, "is_parallel": true, "self": 0.00041981600020335463, "children": { "_process_rank_one_or_two_observation": { "total": 0.001563386999805516, "count": 8, "is_parallel": true, "self": 0.001563386999805516 } } } } } } }, "UnityEnvironment.step": { "total": 2003.268141167012, "count": 63900, "is_parallel": true, "self": 50.54075389499576, "children": { "UnityEnvironment._generate_step_input": { "total": 31.119446010002378, "count": 63900, "is_parallel": true, "self": 31.119446010002378 }, "communicator.exchange": { "total": 1790.2953599210011, "count": 63900, "is_parallel": true, "self": 1790.2953599210011 }, "steps_from_proto": { "total": 131.31258134101273, "count": 63900, "is_parallel": true, "self": 28.295986214030847, "children": { "_process_rank_one_or_two_observation": { "total": 103.01659512698188, "count": 511200, "is_parallel": true, "self": 103.01659512698188 } } } } } } } } } } }, "trainer_advance": { "total": 1109.0067859970077, "count": 63901, "self": 4.271272413020824, "children": { "process_trajectory": { "total": 172.4996754099912, "count": 63901, "self": 172.14421187199088, "children": { "RLTrainer._checkpoint": { "total": 0.35546353800032193, "count": 2, "self": 0.35546353800032193 } } }, "_update_policy": { "total": 932.2358381739957, "count": 444, "self": 374.8597494629886, "children": { "TorchPPOOptimizer.update": { "total": 557.3760887110071, "count": 22812, "self": 557.3760887110071 } } } } } } }, "trainer_threads": { "total": 1.1099996299890336e-06, "count": 1, "self": 1.1099996299890336e-06 }, "TrainerController._save_models": { "total": 0.09473574799994822, "count": 1, "self": 0.002034397999977955, "children": { "RLTrainer._checkpoint": { "total": 0.09270134999997026, "count": 1, "self": 0.09270134999997026 } } } } } } }