{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.25651466846466064, "min": 0.2525632381439209, "max": 1.4325461387634277, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7703.6484375, "min": 7593.06103515625, "max": 43457.71875, "count": 33 }, "Pyramids.Step.mean": { "value": 989899.0, "min": 29991.0, "max": 989899.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989899.0, "min": 29991.0, "max": 989899.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6499873995780945, "min": -0.10363183915615082, "max": 0.6499873995780945, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 180.69650268554688, "min": -25.182537078857422, "max": 184.13665771484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027899697422981262, "min": -0.019118772819638252, "max": 0.28419408202171326, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.756115913391113, "min": -5.27678108215332, "max": 67.63819122314453, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07009995238955266, "min": 0.06444303388205971, "max": 0.07311920836004782, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9813993334537372, "min": 0.5849536668803825, "max": 1.0681378810938136, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015089859151062443, "min": 0.0006467865933891398, "max": 0.018154294068586926, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2112580281148742, "min": 0.008408225714058817, "max": 0.25416011696021695, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.654426019985712e-06, "min": 7.654426019985712e-06, "max": 0.00029522238909253753, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010716196427979997, "min": 0.00010716196427979997, "max": 0.0036341932886022996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255144285714288, "min": 0.10255144285714288, "max": 0.19840746250000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357202000000002, "min": 1.4357202000000002, "max": 2.6113977000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002648891414285714, "min": 0.0002648891414285714, "max": 0.00984090550375, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00370844798, "min": 0.00370844798, "max": 0.12115863023000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014325149357318878, "min": 0.014325149357318878, "max": 0.4856732487678528, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2005520910024643, "min": 0.2005520910024643, "max": 3.8853859901428223, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 292.7551020408163, "min": 277.1261261261261, "max": 998.46875, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28690.0, "min": 15895.0, "max": 32648.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6664142693031807, "min": -0.9368250509724021, "max": 1.6664142693031807, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 163.3085983917117, "min": -29.978401631116867, "max": 181.23579808324575, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6664142693031807, "min": -0.9368250509724021, "max": 1.6664142693031807, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 163.3085983917117, "min": -29.978401631116867, "max": 181.23579808324575, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043623686764550834, "min": 0.043623686764550834, "max": 9.820454163942486, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.275121302925982, "min": 4.275121302925982, "max": 157.12726662307978, "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": "1688428266", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1688430517" }, "total": 2251.386240387, "count": 1, "self": 0.7698637969997435, "children": { "run_training.setup": { "total": 0.03798111800006154, "count": 1, "self": 0.03798111800006154 }, "TrainerController.start_learning": { "total": 2250.578395472, "count": 1, "self": 1.2400004740084114, "children": { "TrainerController._reset_env": { "total": 3.991391161000138, "count": 1, "self": 3.991391161000138 }, "TrainerController.advance": { "total": 2245.206806455991, "count": 64318, "self": 1.3655590939815738, "children": { "env_step": { "total": 1587.3909127529698, "count": 64318, "self": 1483.1015382911055, "children": { "SubprocessEnvManager._take_step": { "total": 103.55257555395337, "count": 64318, "self": 4.608934490021966, "children": { "TorchPolicy.evaluate": { "total": 98.94364106393141, "count": 62559, "self": 98.94364106393141 } } }, "workers": { "total": 0.736798907910952, "count": 64318, "self": 0.0, "children": { "worker_root": { "total": 2245.5572439709927, "count": 64318, "is_parallel": true, "self": 870.8309944419602, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018379519999598415, "count": 1, "is_parallel": true, "self": 0.0005385699996622861, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012993820002975554, "count": 8, "is_parallel": true, "self": 0.0012993820002975554 } } }, "UnityEnvironment.step": { "total": 0.04555546200003846, "count": 1, "is_parallel": true, "self": 0.0005670900002314738, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004781049999564857, "count": 1, "is_parallel": true, "self": 0.0004781049999564857 }, "communicator.exchange": { "total": 0.04264530899990859, "count": 1, "is_parallel": true, "self": 0.04264530899990859 }, "steps_from_proto": { "total": 0.0018649579999419075, "count": 1, "is_parallel": true, "self": 0.0003621110004132788, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015028469995286287, "count": 8, "is_parallel": true, "self": 0.0015028469995286287 } } } } } } }, "UnityEnvironment.step": { "total": 1374.7262495290324, "count": 64317, "is_parallel": true, "self": 32.63152349395159, "children": { "UnityEnvironment._generate_step_input": { "total": 22.199347855038923, "count": 64317, "is_parallel": true, "self": 22.199347855038923 }, "communicator.exchange": { "total": 1220.2554226730726, "count": 64317, "is_parallel": true, "self": 1220.2554226730726 }, "steps_from_proto": { "total": 99.63995550696927, "count": 64317, "is_parallel": true, "self": 19.247566304864677, "children": { "_process_rank_one_or_two_observation": { "total": 80.3923892021046, "count": 514536, "is_parallel": true, "self": 80.3923892021046 } } } } } } } } } } }, "trainer_advance": { "total": 656.4503346090398, "count": 64318, "self": 2.4924567271027627, "children": { "process_trajectory": { "total": 107.6945039419345, "count": 64318, "self": 107.39149846993473, "children": { "RLTrainer._checkpoint": { "total": 0.3030054719997679, "count": 2, "self": 0.3030054719997679 } } }, "_update_policy": { "total": 546.2633739400026, "count": 462, "self": 356.81270226902984, "children": { "TorchPPOOptimizer.update": { "total": 189.45067167097272, "count": 22797, "self": 189.45067167097272 } } } } } } }, "trainer_threads": { "total": 1.1239999366807751e-06, "count": 1, "self": 1.1239999366807751e-06 }, "TrainerController._save_models": { "total": 0.14019625700029792, "count": 1, "self": 0.001820207000037044, "children": { "RLTrainer._checkpoint": { "total": 0.13837605000026088, "count": 1, "self": 0.13837605000026088 } } } } } } }