{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3313358724117279, "min": 0.3313358724117279, "max": 1.5232268571853638, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10024.8984375, "min": 10024.8984375, "max": 46208.609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989981.0, "min": 29952.0, "max": 989981.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7041037082672119, "min": -0.18910381197929382, "max": 0.7130100131034851, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 207.71060180664062, "min": -44.817604064941406, "max": 207.71060180664062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006420732941478491, "min": -0.013690292835235596, "max": 0.19670584797859192, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.8941161632537842, "min": -3.44995379447937, "max": 47.20940399169922, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07049241157493838, "min": 0.0662944723407432, "max": 0.07378557224350708, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9868937620491374, "min": 0.49156973945162924, "max": 1.050834179778273, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015472461102861018, "min": 0.00014034739460466896, "max": 0.01665479744302242, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21661445544005425, "min": 0.0015438213406513586, "max": 0.23316716420231387, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.598133181607143e-06, "min": 7.598133181607143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001063738645425, "min": 0.0001063738645425, "max": 0.0030243233918922996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253267857142856, "min": 0.10253267857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354574999999998, "min": 1.3691136000000002, "max": 2.4004721000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002630145892857143, "min": 0.0002630145892857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036822042500000004, "min": 0.0036822042500000004, "max": 0.10083995923, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010758325457572937, "min": 0.010758325457572937, "max": 0.28104931116104126, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15061655640602112, "min": 0.15061655640602112, "max": 1.9673452377319336, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 265.125, "min": 265.125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29694.0, "min": 15984.0, "max": 33312.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.716456625050148, "min": -1.0000000521540642, "max": 1.7287452662328504, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 193.95959863066673, "min": -32.000001668930054, "max": 193.95959863066673, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.716456625050148, "min": -1.0000000521540642, "max": 1.7287452662328504, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 193.95959863066673, "min": -32.000001668930054, "max": 193.95959863066673, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029397576572028385, "min": 0.029397576572028385, "max": 5.442213462200016, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3219261526392074, "min": 3.3219261526392074, "max": 87.07541539520025, "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": "1773215580", "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/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": "1773217770" }, "total": 2190.162697758, "count": 1, "self": 0.4845877510001628, "children": { "run_training.setup": { "total": 0.025453147999996872, "count": 1, "self": 0.025453147999996872 }, "TrainerController.start_learning": { "total": 2189.6526568589998, "count": 1, "self": 1.3034960630257046, "children": { "TrainerController._reset_env": { "total": 3.0923046819999627, "count": 1, "self": 3.0923046819999627 }, "TrainerController.advance": { "total": 2185.1812371749743, "count": 64024, "self": 1.3060687019656143, "children": { "env_step": { "total": 1525.485516516024, "count": 64024, "self": 1378.9493968290467, "children": { "SubprocessEnvManager._take_step": { "total": 145.74794852004936, "count": 64024, "self": 4.432066226033157, "children": { "TorchPolicy.evaluate": { "total": 141.3158822940162, "count": 62570, "self": 141.3158822940162 } } }, "workers": { "total": 0.7881711669280094, "count": 64024, "self": 0.0, "children": { "worker_root": { "total": 2182.66603305604, "count": 64024, "is_parallel": true, "self": 918.3822253070944, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004860788999963006, "count": 1, "is_parallel": true, "self": 0.003627796999921884, "children": { "_process_rank_one_or_two_observation": { "total": 0.001232992000041122, "count": 8, "is_parallel": true, "self": 0.001232992000041122 } } }, "UnityEnvironment.step": { "total": 0.050974730000007185, "count": 1, "is_parallel": true, "self": 0.0005510490000233403, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004775400000198715, "count": 1, "is_parallel": true, "self": 0.0004775400000198715 }, "communicator.exchange": { "total": 0.04829682199999752, "count": 1, "is_parallel": true, "self": 0.04829682199999752 }, "steps_from_proto": { "total": 0.0016493189999664537, "count": 1, "is_parallel": true, "self": 0.00035868799966465303, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012906310003018007, "count": 8, "is_parallel": true, "self": 0.0012906310003018007 } } } } } } }, "UnityEnvironment.step": { "total": 1264.2838077489455, "count": 64023, "is_parallel": true, "self": 34.8001798548853, "children": { "UnityEnvironment._generate_step_input": { "total": 22.65301102803005, "count": 64023, "is_parallel": true, "self": 22.65301102803005 }, "communicator.exchange": { "total": 1103.4277026960256, "count": 64023, "is_parallel": true, "self": 1103.4277026960256 }, "steps_from_proto": { "total": 103.40291417000458, "count": 64023, "is_parallel": true, "self": 21.896491365921975, "children": { "_process_rank_one_or_two_observation": { "total": 81.5064228040826, "count": 512184, "is_parallel": true, "self": 81.5064228040826 } } } } } } } } } } }, "trainer_advance": { "total": 658.3896519569844, "count": 64024, "self": 2.4343632859850004, "children": { "process_trajectory": { "total": 123.54277889500031, "count": 64024, "self": 123.33752631400012, "children": { "RLTrainer._checkpoint": { "total": 0.20525258100019528, "count": 2, "self": 0.20525258100019528 } } }, "_update_policy": { "total": 532.4125097759991, "count": 434, "self": 294.8218541450144, "children": { "TorchPPOOptimizer.update": { "total": 237.59065563098466, "count": 22815, "self": 237.59065563098466 } } } } } } }, "trainer_threads": { "total": 8.719998731976375e-07, "count": 1, "self": 8.719998731976375e-07 }, "TrainerController._save_models": { "total": 0.07561806700005036, "count": 1, "self": 0.001038195000091946, "children": { "RLTrainer._checkpoint": { "total": 0.07457987199995841, "count": 1, "self": 0.07457987199995841 } } } } } } }