{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0084072351455688, "min": 1.0084072351455688, "max": 1.4486198425292969, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 30203.8125, "min": 30203.8125, "max": 43945.33203125, "count": 3 }, "Pyramids.Step.mean": { "value": 89959.0, "min": 29952.0, "max": 89959.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89959.0, "min": 29952.0, "max": 89959.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.11876195669174194, "min": -0.17233482003211975, "max": -0.11557154357433319, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -28.621631622314453, "min": -40.843353271484375, "max": -27.737171173095703, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1888592392206192, "min": 0.14808136224746704, "max": 0.2780758738517761, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 45.51507568359375, "min": 35.09528350830078, "max": 66.73821258544922, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0699047514213747, "min": 0.06853637551732929, "max": 0.07340234057489005, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6291427627923724, "min": 0.5138163840242304, "max": 0.6853637551732928, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0002980919573567753, "min": 0.0002980919573567753, "max": 0.005309582928191223, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0026828276162109777, "min": 0.0026828276162109777, "max": 0.03716708049733856, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.475240841588888e-05, "min": 7.475240841588888e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0006727716757429999, "min": 0.0006727716757429999, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12491744444444447, "min": 0.12491744444444447, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.1242570000000003, "min": 1.1242570000000003, "max": 1.5538100000000004, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0024992527000000002, "min": 0.0024992527000000002, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.0224932743, "min": 0.0224932743, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.1253610998392105, "min": 0.1253610998392105, "max": 0.42530345916748047, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.1282498836517334, "min": 1.1282498836517334, "max": 2.9771242141723633, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 998.21875, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31968.0, "min": 15984.0, "max": 31968.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.999987552408129, "min": -1.0000000521540642, "max": -0.9366813041269779, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -31.999601677060127, "min": -31.999601677060127, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.999987552408129, "min": -1.0000000521540642, "max": -0.9366813041269779, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -31.999601677060127, "min": -31.999601677060127, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.4579127598553896, "min": 1.4579127598553896, "max": 7.957944795489311, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 46.65320831537247, "min": 46.65320831537247, "max": 127.32711672782898, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1754320435", "python_version": "3.10.12 (main, May 27 2025, 17:12:29) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1754320624" }, "total": 188.66603585099995, "count": 1, "self": 0.43928104099984466, "children": { "run_training.setup": { "total": 0.0226098750000574, "count": 1, "self": 0.0226098750000574 }, "TrainerController.start_learning": { "total": 188.20414493500004, "count": 1, "self": 0.1096155679954336, "children": { "TrainerController._reset_env": { "total": 3.0826018330000124, "count": 1, "self": 3.0826018330000124 }, "TrainerController.advance": { "total": 184.86671524900453, "count": 6261, "self": 0.12537020600950655, "children": { "env_step": { "total": 120.39181705299825, "count": 6261, "self": 105.90756587200644, "children": { "SubprocessEnvManager._take_step": { "total": 14.408356249992266, "count": 6261, "self": 0.4365564079927253, "children": { "TorchPolicy.evaluate": { "total": 13.971799841999541, "count": 6256, "self": 13.971799841999541 } } }, "workers": { "total": 0.0758949309995387, "count": 6261, "self": 0.0, "children": { "worker_root": { "total": 187.36879488699742, "count": 6261, "is_parallel": true, "self": 91.329450005995, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0039028239999652214, "count": 1, "is_parallel": true, "self": 0.0027007869998669776, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012020370000982439, "count": 8, "is_parallel": true, "self": 0.0012020370000982439 } } }, "UnityEnvironment.step": { "total": 0.04974213899993174, "count": 1, "is_parallel": true, "self": 0.0005520580000393238, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045894300001236843, "count": 1, "is_parallel": true, "self": 0.00045894300001236843 }, "communicator.exchange": { "total": 0.046993752999924254, "count": 1, "is_parallel": true, "self": 0.046993752999924254 }, "steps_from_proto": { "total": 0.0017373849999557933, "count": 1, "is_parallel": true, "self": 0.00036726799976349866, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013701170001922947, "count": 8, "is_parallel": true, "self": 0.0013701170001922947 } } } } } } }, "UnityEnvironment.step": { "total": 96.03934488100242, "count": 6260, "is_parallel": true, "self": 3.1190368900154226, "children": { "UnityEnvironment._generate_step_input": { "total": 2.1486383629969623, "count": 6260, "is_parallel": true, "self": 2.1486383629969623 }, "communicator.exchange": { "total": 81.64103524599636, "count": 6260, "is_parallel": true, "self": 81.64103524599636 }, "steps_from_proto": { "total": 9.130634381993673, "count": 6260, "is_parallel": true, "self": 1.7897271370123917, "children": { "_process_rank_one_or_two_observation": { "total": 7.340907244981281, "count": 50080, "is_parallel": true, "self": 7.340907244981281 } } } } } } } } } } }, "trainer_advance": { "total": 64.34952798999677, "count": 6261, "self": 0.14149697599066258, "children": { "process_trajectory": { "total": 11.312052734006329, "count": 6261, "self": 11.312052734006329 }, "_update_policy": { "total": 52.89597827999978, "count": 30, "self": 29.40393100099982, "children": { "TorchPPOOptimizer.update": { "total": 23.492047278999962, "count": 2295, "self": 23.492047278999962 } } } } } } }, "trainer_threads": { "total": 1.2579999975059764e-06, "count": 1, "self": 1.2579999975059764e-06 }, "TrainerController._save_models": { "total": 0.14521102700007305, "count": 1, "self": 0.0011326870001084899, "children": { "RLTrainer._checkpoint": { "total": 0.14407833999996456, "count": 1, "self": 0.14407833999996456 } } } } } } }