{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4589023292064667, "min": 0.4515879154205322, "max": 1.479384183883667, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13708.330078125, "min": 13668.373046875, "max": 44878.59765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989950.0, "min": 29983.0, "max": 989950.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989950.0, "min": 29983.0, "max": 989950.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5477195382118225, "min": -0.09488475322723389, "max": 0.5617650747299194, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.52743530273438, "min": -22.867225646972656, "max": 154.67462158203125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0283465925604105, "min": -0.0283465925604105, "max": 0.5623253583908081, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -7.738619804382324, "min": -7.738619804382324, "max": 133.83343505859375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06695607338181055, "min": 0.06477423020112404, "max": 0.07341936773099449, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9373850273453477, "min": 0.5764700961188485, "max": 1.0570274153684367, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013832345376570066, "min": 0.00018678295763856296, "max": 0.015087817980907093, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19365283527198093, "min": 0.0024281784493013184, "max": 0.2263172697136064, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.6189831746571455e-06, "min": 7.6189831746571455e-06, "max": 0.0002948509142163625, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010666576444520004, "min": 0.00010666576444520004, "max": 0.0036085368971544, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253962857142858, "min": 0.10253962857142858, "max": 0.1982836375, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355548, "min": 1.4355548, "max": 2.5692707000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026370889428571436, "min": 0.00026370889428571436, "max": 0.00982853538625, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003691924520000001, "min": 0.003691924520000001, "max": 0.12029427543999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008472343906760216, "min": 0.008472343906760216, "max": 0.40389949083328247, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11861281841993332, "min": 0.11861281841993332, "max": 3.2311959266662598, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 327.57471264367814, "min": 327.57471264367814, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28499.0, "min": 16398.0, "max": 33359.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6034321676211796, "min": -0.9999125525355339, "max": 1.621241290041286, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.49859858304262, "min": -31.997201681137085, "max": 149.1541986837983, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6034321676211796, "min": -0.9999125525355339, "max": 1.621241290041286, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.49859858304262, "min": -31.997201681137085, "max": 149.1541986837983, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02928713660074355, "min": 0.02928713660074355, "max": 8.771334750687375, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.547980884264689, "min": 2.547980884264689, "max": 149.11269076168537, "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": "1707631964", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707634101" }, "total": 2137.253467673, "count": 1, "self": 0.4900891649999721, "children": { "run_training.setup": { "total": 0.050336036999851785, "count": 1, "self": 0.050336036999851785 }, "TrainerController.start_learning": { "total": 2136.7130424710003, "count": 1, "self": 1.3599783709992153, "children": { "TrainerController._reset_env": { "total": 2.980794421999917, "count": 1, "self": 2.980794421999917 }, "TrainerController.advance": { "total": 2132.2800787880014, "count": 63721, "self": 1.4611385699481616, "children": { "env_step": { "total": 1514.3499935800091, "count": 63721, "self": 1382.3317186240356, "children": { "SubprocessEnvManager._take_step": { "total": 131.16101300297532, "count": 63721, "self": 4.70067322997329, "children": { "TorchPolicy.evaluate": { "total": 126.46033977300203, "count": 62547, "self": 126.46033977300203 } } }, "workers": { "total": 0.8572619529982148, "count": 63721, "self": 0.0, "children": { "worker_root": { "total": 2131.609183742929, "count": 63721, "is_parallel": true, "self": 865.3593898669155, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020589360001395107, "count": 1, "is_parallel": true, "self": 0.0006781700003557489, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013807659997837618, "count": 8, "is_parallel": true, "self": 0.0013807659997837618 } } }, "UnityEnvironment.step": { "total": 0.05371725500003777, "count": 1, "is_parallel": true, "self": 0.0006683179999527056, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005147260001194809, "count": 1, "is_parallel": true, "self": 0.0005147260001194809 }, "communicator.exchange": { "total": 0.05080268899996554, "count": 1, "is_parallel": true, "self": 0.05080268899996554 }, "steps_from_proto": { "total": 0.0017315220000000409, "count": 1, "is_parallel": true, "self": 0.0003692729999329458, "children": { "_process_rank_one_or_two_observation": { "total": 0.001362249000067095, "count": 8, "is_parallel": true, "self": 0.001362249000067095 } } } } } } }, "UnityEnvironment.step": { "total": 1266.2497938760134, "count": 63720, "is_parallel": true, "self": 35.306922262220496, "children": { "UnityEnvironment._generate_step_input": { "total": 25.599639962938, "count": 63720, "is_parallel": true, "self": 25.599639962938 }, "communicator.exchange": { "total": 1103.0195869279596, "count": 63720, "is_parallel": true, "self": 1103.0195869279596 }, "steps_from_proto": { "total": 102.32364472289532, "count": 63720, "is_parallel": true, "self": 20.834907768874928, "children": { "_process_rank_one_or_two_observation": { "total": 81.4887369540204, "count": 509760, "is_parallel": true, "self": 81.4887369540204 } } } } } } } } } } }, "trainer_advance": { "total": 616.4689466380441, "count": 63721, "self": 2.639158955037601, "children": { "process_trajectory": { "total": 125.79031467400569, "count": 63721, "self": 125.5780535260053, "children": { "RLTrainer._checkpoint": { "total": 0.21226114800037976, "count": 2, "self": 0.21226114800037976 } } }, "_update_policy": { "total": 488.03947300900086, "count": 454, "self": 286.3714463629965, "children": { "TorchPPOOptimizer.update": { "total": 201.66802664600436, "count": 22788, "self": 201.66802664600436 } } } } } } }, "trainer_threads": { "total": 9.379996299685445e-07, "count": 1, "self": 9.379996299685445e-07 }, "TrainerController._save_models": { "total": 0.09218995199989877, "count": 1, "self": 0.0013932379997640965, "children": { "RLTrainer._checkpoint": { "total": 0.09079671400013467, "count": 1, "self": 0.09079671400013467 } } } } } } }