{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.2501046657562256, "min": 1.1939489841461182, "max": 1.5913022756576538, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 12381.037109375, "min": 11790.4853515625, "max": 16294.935546875, "count": 50 }, "Pyramids.Step.mean": { "value": 499999.0, "min": 9984.0, "max": 499999.0, "count": 50 }, "Pyramids.Step.sum": { "value": 499999.0, "min": 9984.0, "max": 499999.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09566681832075119, "min": -0.10525472462177277, "max": -0.0065712472423911095, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -15.5936918258667, "min": -16.94601058959961, "max": -1.0251145362854004, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06379649303669699, "min": 0.058526400409863094, "max": 0.07473665089303351, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.31898246518348494, "min": 0.17557920122958928, "max": 0.31898246518348494, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 2.9341412917011963e-05, "min": 6.6490340257827375e-06, "max": 0.01349384894597784, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0001467070645850598, "min": 2.106097124378865e-05, "max": 0.04048154683793352, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.260858913079994e-06, "min": 3.260858913079994e-06, "max": 0.00029631360122879996, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.630429456539997e-05, "min": 1.630429456539997e-05, "max": 0.0011168256277248, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10108692, "min": 0.10108692, "max": 0.1987712, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.5054346, "min": 0.3514752, "max": 0.7722752, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.0001185833079999998, "min": 0.0001185833079999998, "max": 0.00987724288, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.000592916539999999, "min": 0.000592916539999999, "max": 0.037230292479999996, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 746.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15984.0, "min": 746.0, "max": 15984.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9999375445768237, "min": -1.0000000447034836, "max": 1.253999911248684, "count": 38 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -15.99900071322918, "min": -16.000000715255737, "max": 1.253999911248684, "count": 38 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9999375445768237, "min": -1.0000000447034836, "max": 1.253999911248684, "count": 38 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -15.99900071322918, "min": -16.000000715255737, "max": 1.253999911248684, "count": 38 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1792705072", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn config/ppo/Pyramids.yaml --env=training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --max-lifetime-restarts=0", "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": "1792706043" }, "total": 971.5753852080002, "count": 1, "self": 1.224815710000712, "children": { "run_training.setup": { "total": 0.039954345999831276, "count": 1, "self": 0.039954345999831276 }, "TrainerController.start_learning": { "total": 970.3106151519996, "count": 1, "self": 0.9546815610224257, "children": { "TrainerController._reset_env": { "total": 5.233627830000387, "count": 1, "self": 5.233627830000387 }, "TrainerController.advance": { "total": 964.0717236049777, "count": 31266, "self": 1.1823989049526062, "children": { "env_step": { "total": 760.9018197400419, "count": 31266, "self": 702.4233536260522, "children": { "SubprocessEnvManager._take_step": { "total": 57.84238519898872, "count": 31266, "self": 2.555585806970612, "children": { "TorchPolicy.evaluate": { "total": 55.28679939201811, "count": 31259, "self": 55.28679939201811 } } }, "workers": { "total": 0.6360809150010027, "count": 31266, "self": 0.0, "children": { "worker_root": { "total": 966.6629856819791, "count": 31266, "is_parallel": true, "self": 337.1782518049654, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004418220000388828, "count": 1, "is_parallel": true, "self": 0.0011062109992963087, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033120090010925196, "count": 8, "is_parallel": true, "self": 0.0033120090010925196 } } }, "UnityEnvironment.step": { "total": 0.06671823400029098, "count": 1, "is_parallel": true, "self": 0.0005583110005318304, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005306699999891862, "count": 1, "is_parallel": true, "self": 0.0005306699999891862 }, "communicator.exchange": { "total": 0.06134799399978874, "count": 1, "is_parallel": true, "self": 0.06134799399978874 }, "steps_from_proto": { "total": 0.004281258999981219, "count": 1, "is_parallel": true, "self": 0.00035039899967159727, "children": { "_process_rank_one_or_two_observation": { "total": 0.003930860000309622, "count": 8, "is_parallel": true, "self": 0.003930860000309622 } } } } } } }, "UnityEnvironment.step": { "total": 629.4847338770137, "count": 31265, "is_parallel": true, "self": 18.183061656024165, "children": { "UnityEnvironment._generate_step_input": { "total": 12.60300877101281, "count": 31265, "is_parallel": true, "self": 12.60300877101281 }, "communicator.exchange": { "total": 545.9632927780003, "count": 31265, "is_parallel": true, "self": 545.9632927780003 }, "steps_from_proto": { "total": 52.7353706719764, "count": 31265, "is_parallel": true, "self": 11.924669101853851, "children": { "_process_rank_one_or_two_observation": { "total": 40.810701570122546, "count": 250120, "is_parallel": true, "self": 40.810701570122546 } } } } } } } } } } }, "trainer_advance": { "total": 201.9875049599832, "count": 31266, "self": 1.2953820219277077, "children": { "process_trajectory": { "total": 43.992623443059074, "count": 31266, "self": 43.63490549005883, "children": { "RLTrainer._checkpoint": { "total": 0.3577179530002468, "count": 1, "self": 0.3577179530002468 } } }, "_update_policy": { "total": 156.69949949499642, "count": 172, "self": 81.5224108859843, "children": { "TorchPPOOptimizer.update": { "total": 75.17708860901212, "count": 11655, "self": 75.17708860901212 } } } } } } }, "trainer_threads": { "total": 9.99999429041054e-07, "count": 1, "self": 9.99999429041054e-07 }, "TrainerController._save_models": { "total": 0.05058115599968005, "count": 1, "self": 0.0012254599996595061, "children": { "RLTrainer._checkpoint": { "total": 0.049355696000020544, "count": 1, "self": 0.049355696000020544 } } } } } } }