{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4971546530723572, "min": 0.4362412691116333, "max": 1.4447790384292603, "count": 55 }, "Pyramids.Policy.Entropy.sum": { "value": 14731.6865234375, "min": 12912.7412109375, "max": 43828.81640625, "count": 55 }, "Pyramids.Step.mean": { "value": 1649884.0, "min": 29964.0, "max": 1649884.0, "count": 55 }, "Pyramids.Step.sum": { "value": 1649884.0, "min": 29964.0, "max": 1649884.0, "count": 55 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4773726761341095, "min": -0.09652943909168243, "max": 0.5211503505706787, "count": 55 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.84536743164062, "min": -23.263595581054688, "max": 140.71060180664062, "count": 55 }, "Pyramids.Policy.CuriosityValueEstimate.mean": { "value": 0.13597719371318817, "min": 0.12402014434337616, "max": 0.4941040575504303, "count": 55 }, "Pyramids.Policy.CuriosityValueEstimate.sum": { "value": 36.98579788208008, "min": 33.48543930053711, "max": 118.58497619628906, "count": 55 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06851170499603973, "min": 0.06421045258705858, "max": 0.07541829284405431, "count": 55 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9591638699445562, "min": 0.5180986454923123, "max": 1.0749155323913633, "count": 55 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014964399547135968, "min": 0.0001916125990513812, "max": 0.014964399547135968, "count": 55 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20950159365990356, "min": 0.0026825763867193366, "max": 0.20950159365990356, "count": 55 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002509563592050285, "min": 0.0002509563592050285, "max": 0.0002995150630187886, "count": 55 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.003513389028870399, "min": 0.00209660544113152, "max": 0.00416933828022061, "count": 55 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.18365211428571432, "min": 0.18365211428571432, "max": 0.1998383542857143, "count": 55 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.5711296000000003, "min": 1.3988684800000002, "max": 2.88977939, "count": 55 }, "Pyramids.Policy.Beta.mean": { "value": 0.008366846217142856, "min": 0.008366846217142856, "max": 0.009983851593142858, "count": 55 }, "Pyramids.Policy.Beta.sum": { "value": 0.11713584703999999, "min": 0.06988696115200001, "max": 0.13898896106099998, "count": 55 }, "Pyramids.Losses.CuriosityForwardLoss.mean": { "value": 0.05367062721190797, "min": 0.053076746675618916, "max": 0.4528611260168071, "count": 55 }, "Pyramids.Losses.CuriosityForwardLoss.sum": { "value": 0.7513887809667116, "min": 0.7430744534586649, "max": 3.1700278821176497, "count": 55 }, "Pyramids.Losses.CuriosityInverseLoss.mean": { "value": 0.046715698617585344, "min": 0.04542394133882825, "max": 0.7134430838369555, "count": 55 }, "Pyramids.Losses.CuriosityInverseLoss.sum": { "value": 0.6540197806461948, "min": 0.6359351787435955, "max": 4.994101586858688, "count": 55 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 376.5, "min": 376.5, "max": 999.0, "count": 55 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31626.0, "min": 16763.0, "max": 32835.0, "count": 55 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.552049982583239, "min": -0.9998968260422829, "max": 1.552049982583239, "count": 55 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.37219853699207, "min": -30.996801607310772, "max": 130.37219853699207, "count": 55 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.552049982583239, "min": -0.9998968260422829, "max": 1.552049982583239, "count": 55 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.37219853699207, "min": -30.996801607310772, "max": 130.37219853699207, "count": 55 }, "Pyramids.Policy.CuriosityReward.mean": { "value": 0.4238290424303462, "min": 0.4238290424303462, "max": 7.0742058644399926, "count": 55 }, "Pyramids.Policy.CuriosityReward.sum": { "value": 35.60163956414908, "min": 33.339902056381106, "max": 165.2631748020649, "count": 55 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 55 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 55 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706849376", "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/Pyramids.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 2 --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": "1706853371" }, "total": 3995.5396693479997, "count": 1, "self": 0.6888687909995497, "children": { "run_training.setup": { "total": 0.054667008998876554, "count": 1, "self": 0.054667008998876554 }, "TrainerController.start_learning": { "total": 3994.7961335480013, "count": 1, "self": 2.962365419332855, "children": { "TrainerController._reset_env": { "total": 3.3744601719990897, "count": 1, "self": 3.3744601719990897 }, "TrainerController.advance": { "total": 3988.2568488346697, "count": 105022, "self": 2.928418232291733, "children": { "env_step": { "total": 2690.687441987682, "count": 105022, "self": 2447.37435147424, "children": { "SubprocessEnvManager._take_step": { "total": 241.6054076482833, "count": 105022, "self": 8.805088753213568, "children": { "TorchPolicy.evaluate": { "total": 232.80031889506972, "count": 103595, "self": 232.80031889506972 } } }, "workers": { "total": 1.7076828651588585, "count": 105021, "self": 0.0, "children": { "worker_root": { "total": 3985.234329409752, "count": 105021, "is_parallel": true, "self": 1753.0573025406502, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005755326001235517, "count": 1, "is_parallel": true, "self": 0.004259782001099666, "children": { "_process_rank_one_or_two_observation": { "total": 0.001495544000135851, "count": 8, "is_parallel": true, "self": 0.001495544000135851 } } }, "UnityEnvironment.step": { "total": 0.05339855300007912, "count": 1, "is_parallel": true, "self": 0.0005940259979979601, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004901690008409787, "count": 1, "is_parallel": true, "self": 0.0004901690008409787 }, "communicator.exchange": { "total": 0.05063567800061719, "count": 1, "is_parallel": true, "self": 0.05063567800061719 }, "steps_from_proto": { "total": 0.0016786800006229896, "count": 1, "is_parallel": true, "self": 0.00035694800499186385, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013217319956311258, "count": 8, "is_parallel": true, "self": 0.0013217319956311258 } } } } } } }, "UnityEnvironment.step": { "total": 2232.1770268691016, "count": 105020, "is_parallel": true, "self": 62.91356006303431, "children": { "UnityEnvironment._generate_step_input": { "total": 43.06952516277852, "count": 105020, "is_parallel": true, "self": 43.06952516277852 }, "communicator.exchange": { "total": 1952.18166853386, "count": 105020, "is_parallel": true, "self": 1952.18166853386 }, "steps_from_proto": { "total": 174.01227310942886, "count": 105020, "is_parallel": true, "self": 36.1116500932294, "children": { "_process_rank_one_or_two_observation": { "total": 137.90062301619946, "count": 840160, "is_parallel": true, "self": 137.90062301619946 } } } } } } } } } } }, "trainer_advance": { "total": 1294.6409886146957, "count": 105021, "self": 5.383857938812071, "children": { "process_trajectory": { "total": 212.04104393490525, "count": 105021, "self": 211.7207984099059, "children": { "RLTrainer._checkpoint": { "total": 0.32024552499933634, "count": 3, "self": 0.32024552499933634 } } }, "_update_policy": { "total": 1077.2160867409784, "count": 756, "self": 710.9738556430439, "children": { "TorchPPOOptimizer.update": { "total": 366.24223109793456, "count": 37683, "self": 366.24223109793456 } } } } } } }, "trainer_threads": { "total": 1.2580003385664895e-06, "count": 1, "self": 1.2580003385664895e-06 }, "TrainerController._save_models": { "total": 0.2024578639993706, "count": 1, "self": 0.0021341889987525064, "children": { "RLTrainer._checkpoint": { "total": 0.2003236750006181, "count": 1, "self": 0.2003236750006181 } } } } } } }