{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31931546330451965, "min": 0.31324079632759094, "max": 1.4521349668502808, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9630.5546875, "min": 9357.12890625, "max": 44051.96484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6975789666175842, "min": -0.272569864988327, "max": 0.6975789666175842, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 198.80999755859375, "min": -64.59906005859375, "max": 198.80999755859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01004840712994337, "min": 0.008229592815041542, "max": 0.47631075978279114, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.8637959957122803, "min": 2.1973013877868652, "max": 112.88565063476562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06559790080964809, "min": 0.06559790080964809, "max": 0.07448295098487735, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9183706113350733, "min": 0.5057564832180828, "max": 1.067751356672756, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014806569684185974, "min": 0.00043815759177956047, "max": 0.016199686225531078, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20729197557860363, "min": 0.004381575917795605, "max": 0.24254277272334818, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.451690373278572e-06, "min": 7.451690373278572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010432366522590001, "min": 0.00010432366522590001, "max": 0.0032589740136753998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024838642857143, "min": 0.1024838642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347741, "min": 1.3886848, "max": 2.4858493, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025813804214285717, "min": 0.00025813804214285717, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036139325900000005, "min": 0.0036139325900000005, "max": 0.10865382754, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01382953580468893, "min": 0.01382953580468893, "max": 0.5617789626121521, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19361349940299988, "min": 0.19361349940299988, "max": 3.93245267868042, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 277.45631067961165, "min": 273.24528301886795, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28578.0, "min": 15984.0, "max": 32559.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7021176313214443, "min": -1.0000000521540642, "max": 1.726754701221889, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 173.6159983947873, "min": -30.589401558041573, "max": 183.03599832952023, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7021176313214443, "min": -1.0000000521540642, "max": 1.726754701221889, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 173.6159983947873, "min": -30.589401558041573, "max": 183.03599832952023, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03961917243848838, "min": 0.03961917243848838, "max": 11.13578854687512, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.041155588725815, "min": 4.041155588725815, "max": 178.1726167500019, "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": "1758789977", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [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": "1758792253" }, "total": 2276.301296884, "count": 1, "self": 0.5308441979996132, "children": { "run_training.setup": { "total": 0.03096923200018864, "count": 1, "self": 0.03096923200018864 }, "TrainerController.start_learning": { "total": 2275.739483454, "count": 1, "self": 1.5434628680150126, "children": { "TrainerController._reset_env": { "total": 2.2549415229996157, "count": 1, "self": 2.2549415229996157 }, "TrainerController.advance": { "total": 2271.865511199985, "count": 64126, "self": 1.5262685509369476, "children": { "env_step": { "total": 1611.6721493779864, "count": 64126, "self": 1456.4916511208057, "children": { "SubprocessEnvManager._take_step": { "total": 154.2594781141911, "count": 64126, "self": 4.798168300246289, "children": { "TorchPolicy.evaluate": { "total": 149.4613098139448, "count": 62557, "self": 149.4613098139448 } } }, "workers": { "total": 0.9210201429896188, "count": 64126, "self": 0.0, "children": { "worker_root": { "total": 2269.812782494979, "count": 64126, "is_parallel": true, "self": 933.7273671610092, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001899197000057029, "count": 1, "is_parallel": true, "self": 0.0006291049999163079, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012700920001407212, "count": 8, "is_parallel": true, "self": 0.0012700920001407212 } } }, "UnityEnvironment.step": { "total": 0.05225823399996443, "count": 1, "is_parallel": true, "self": 0.0005746410001847835, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045884699966336484, "count": 1, "is_parallel": true, "self": 0.00045884699966336484 }, "communicator.exchange": { "total": 0.04934073000003991, "count": 1, "is_parallel": true, "self": 0.04934073000003991 }, "steps_from_proto": { "total": 0.0018840160000763717, "count": 1, "is_parallel": true, "self": 0.0004200970006422722, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014639189994340995, "count": 8, "is_parallel": true, "self": 0.0014639189994340995 } } } } } } }, "UnityEnvironment.step": { "total": 1336.0854153339696, "count": 64125, "is_parallel": true, "self": 33.873171795823055, "children": { "UnityEnvironment._generate_step_input": { "total": 24.176790329046526, "count": 64125, "is_parallel": true, "self": 24.176790329046526 }, "communicator.exchange": { "total": 1166.7797517380445, "count": 64125, "is_parallel": true, "self": 1166.7797517380445 }, "steps_from_proto": { "total": 111.25570147105554, "count": 64125, "is_parallel": true, "self": 23.473260051271154, "children": { "_process_rank_one_or_two_observation": { "total": 87.78244141978439, "count": 513000, "is_parallel": true, "self": 87.78244141978439 } } } } } } } } } } }, "trainer_advance": { "total": 658.6670932710617, "count": 64126, "self": 2.8879338011533946, "children": { "process_trajectory": { "total": 128.18365811291233, "count": 64126, "self": 127.99375911591187, "children": { "RLTrainer._checkpoint": { "total": 0.18989899700045498, "count": 2, "self": 0.18989899700045498 } } }, "_update_policy": { "total": 527.595501356996, "count": 447, "self": 294.08744115000945, "children": { "TorchPPOOptimizer.update": { "total": 233.50806020698656, "count": 22824, "self": 233.50806020698656 } } } } } } }, "trainer_threads": { "total": 9.650002539274283e-07, "count": 1, "self": 9.650002539274283e-07 }, "TrainerController._save_models": { "total": 0.07556689800003369, "count": 1, "self": 0.0011185720004505129, "children": { "RLTrainer._checkpoint": { "total": 0.07444832599958318, "count": 1, "self": 0.07444832599958318 } } } } } } }