{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2774597406387329, "min": 0.2774597406387329, "max": 1.483777403831482, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8337.1103515625, "min": 8255.3359375, "max": 45011.87109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989900.0, "min": 29952.0, "max": 989900.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989900.0, "min": 29952.0, "max": 989900.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6007116436958313, "min": -0.11814187467098236, "max": 0.6636748313903809, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.20281982421875, "min": -28.354049682617188, "max": 191.80203247070312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012336531654000282, "min": -0.029433585703372955, "max": 0.24395015835762024, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.51591157913208, "min": -8.359138488769531, "max": 58.548038482666016, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06942741932440027, "min": 0.0651266560349281, "max": 0.07444265751206937, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9719838705416038, "min": 0.4861666555978069, "max": 1.1166398626810405, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018676527718268592, "min": 0.0007435333197436597, "max": 0.018676527718268592, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2614713880557603, "min": 0.005204733238205618, "max": 0.2614713880557603, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.34999040717857e-06, "min": 7.34999040717857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010289986570049998, "min": 0.00010289986570049998, "max": 0.0036327496890835, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024499642857143, "min": 0.1024499642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342995000000003, "min": 1.3691136000000002, "max": 2.6109164999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002547514321428571, "min": 0.0002547514321428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003566520049999999, "min": 0.003566520049999999, "max": 0.12111055835, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01261480338871479, "min": 0.01261480338871479, "max": 0.3979341387748718, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17660725116729736, "min": 0.17660725116729736, "max": 2.785538911819458, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 298.2475247524753, "min": 277.45283018867923, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30123.0, "min": 15984.0, "max": 32464.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5829148384013978, "min": -1.0000000521540642, "max": 1.6848018724682197, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 159.87439867854118, "min": -32.000001668930054, "max": 178.58899848163128, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5829148384013978, "min": -1.0000000521540642, "max": 1.6848018724682197, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 159.87439867854118, "min": -32.000001668930054, "max": 178.58899848163128, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03906513970186196, "min": 0.03906513970186196, "max": 7.644125474616885, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.945579109888058, "min": 3.945579109888058, "max": 122.30600759387016, "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": "1778088501", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/home/lesliebinbin/codings/ml-agents/.venv/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": "1778090167" }, "total": 1665.5673947229516, "count": 1, "self": 0.26922283391468227, "children": { "run_training.setup": { "total": 0.014207420987077057, "count": 1, "self": 0.014207420987077057 }, "TrainerController.start_learning": { "total": 1665.2839644680498, "count": 1, "self": 1.1416613415349275, "children": { "TrainerController._reset_env": { "total": 1.693388284998946, "count": 1, "self": 1.693388284998946 }, "TrainerController.advance": { "total": 1662.3697730294662, "count": 64151, "self": 0.9837138885632157, "children": { "env_step": { "total": 1073.9069227073342, "count": 64151, "self": 882.4164895971771, "children": { "SubprocessEnvManager._take_step": { "total": 190.75584493996575, "count": 64151, "self": 3.3543323969934136, "children": { "TorchPolicy.evaluate": { "total": 187.40151254297234, "count": 62567, "self": 187.40151254297234 } } }, "workers": { "total": 0.7345881701912731, "count": 64151, "self": 0.0, "children": { "worker_root": { "total": 1662.6520749307238, "count": 64151, "is_parallel": true, "self": 848.89608296589, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015558290760964155, "count": 1, "is_parallel": true, "self": 0.0005466641159728169, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010091649601235986, "count": 8, "is_parallel": true, "self": 0.0010091649601235986 } } }, "UnityEnvironment.step": { "total": 0.026647060993127525, "count": 1, "is_parallel": true, "self": 0.00019737007096409798, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018133001867681742, "count": 1, "is_parallel": true, "self": 0.00018133001867681742 }, "communicator.exchange": { "total": 0.025735297007486224, "count": 1, "is_parallel": true, "self": 0.025735297007486224 }, "steps_from_proto": { "total": 0.0005330638960003853, "count": 1, "is_parallel": true, "self": 0.0001287856139242649, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004042782820761204, "count": 8, "is_parallel": true, "self": 0.0004042782820761204 } } } } } } }, "UnityEnvironment.step": { "total": 813.7559919648338, "count": 64150, "is_parallel": true, "self": 11.738852503942326, "children": { "UnityEnvironment._generate_step_input": { "total": 7.756135683273897, "count": 64150, "is_parallel": true, "self": 7.756135683273897 }, "communicator.exchange": { "total": 763.7353502925253, "count": 64150, "is_parallel": true, "self": 763.7353502925253 }, "steps_from_proto": { "total": 30.525653485092334, "count": 64150, "is_parallel": true, "self": 7.217875162488781, "children": { "_process_rank_one_or_two_observation": { "total": 23.307778322603554, "count": 513200, "is_parallel": true, "self": 23.307778322603554 } } } } } } } } } } }, "trainer_advance": { "total": 587.4791364335688, "count": 64151, "self": 2.0148182252887636, "children": { "process_trajectory": { "total": 95.76337434828747, "count": 64151, "self": 95.61310717032757, "children": { "RLTrainer._checkpoint": { "total": 0.15026717795990407, "count": 2, "self": 0.15026717795990407 } } }, "_update_policy": { "total": 489.70094385999255, "count": 452, "self": 213.64967413351405, "children": { "TorchPPOOptimizer.update": { "total": 276.0512697264785, "count": 22776, "self": 276.0512697264785 } } } } } } }, "trainer_threads": { "total": 6.770715117454529e-07, "count": 1, "self": 6.770715117454529e-07 }, "TrainerController._save_models": { "total": 0.07914113497827202, "count": 1, "self": 0.0007529569556936622, "children": { "RLTrainer._checkpoint": { "total": 0.07838817802257836, "count": 1, "self": 0.07838817802257836 } } } } } } }