{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4281761050224304, "min": 0.4281761050224304, "max": 1.4554204940795898, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12886.3876953125, "min": 12886.3876953125, "max": 44151.63671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989887.0, "min": 29952.0, "max": 989887.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989887.0, "min": 29952.0, "max": 989887.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.540825605392456, "min": -0.10513884574174881, "max": 0.540825605392456, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.89035034179688, "min": -25.233322143554688, "max": 150.89035034179688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.2570911943912506, "min": -0.0024904801975935698, "max": 0.3227359354496002, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 71.72843933105469, "min": -0.6724296808242798, "max": 78.10209655761719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06773067277260071, "min": 0.06575720593987387, "max": 0.07282738035104962, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.94822941881641, "min": 0.48600891623920334, "max": 1.0924107052657444, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.019624615633088694, "min": 0.0005098309856467851, "max": 0.019624615633088694, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2747446188632417, "min": 0.005608140842114636, "max": 0.2747446188632417, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.793904544921427e-06, "min": 7.793904544921427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010911466362889997, "min": 0.00010911466362889997, "max": 0.0035077646307451996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025979357142857, "min": 0.1025979357142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4363711, "min": 1.3886848, "max": 2.5724533999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026953377785714287, "min": 0.00026953377785714287, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00377347289, "min": 0.00377347289, "max": 0.11694855452000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010315586812794209, "min": 0.010315586812794209, "max": 0.4765411913394928, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14441820979118347, "min": 0.14441820979118347, "max": 3.3357882499694824, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 319.53932584269666, "min": 319.53932584269666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28439.0, "min": 15984.0, "max": 33045.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5455909926402436, "min": -1.0000000521540642, "max": 1.623474973719567, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 137.55759834498167, "min": -30.999201610684395, "max": 137.55759834498167, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5455909926402436, "min": -1.0000000521540642, "max": 1.623474973719567, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 137.55759834498167, "min": -30.999201610684395, "max": 137.55759834498167, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03442800821766867, "min": 0.03442800821766867, "max": 10.22113867662847, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0640927313725115, "min": 3.0640927313725115, "max": 163.53821882605553, "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": "1768430278", "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 --force", "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": "1768432334" }, "total": 2055.5871585370005, "count": 1, "self": 0.4774882860010621, "children": { "run_training.setup": { "total": 0.022438322999732918, "count": 1, "self": 0.022438322999732918 }, "TrainerController.start_learning": { "total": 2055.0872319279997, "count": 1, "self": 1.1514195557529092, "children": { "TrainerController._reset_env": { "total": 2.1111834739995174, "count": 1, "self": 2.1111834739995174 }, "TrainerController.advance": { "total": 2051.7536914242455, "count": 63787, "self": 1.2394353262898221, "children": { "env_step": { "total": 1420.9957370511383, "count": 63787, "self": 1288.323292848646, "children": { "SubprocessEnvManager._take_step": { "total": 131.9773687813058, "count": 63787, "self": 4.2309299961953, "children": { "TorchPolicy.evaluate": { "total": 127.74643878511051, "count": 62557, "self": 127.74643878511051 } } }, "workers": { "total": 0.6950754211866297, "count": 63787, "self": 0.0, "children": { "worker_root": { "total": 2048.448441334247, "count": 63787, "is_parallel": true, "self": 865.9042970341143, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017860099997051293, "count": 1, "is_parallel": true, "self": 0.0005349969997041626, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012510130000009667, "count": 8, "is_parallel": true, "self": 0.0012510130000009667 } } }, "UnityEnvironment.step": { "total": 0.04654632300025696, "count": 1, "is_parallel": true, "self": 0.0005341870000847848, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042767400009324774, "count": 1, "is_parallel": true, "self": 0.00042767400009324774 }, "communicator.exchange": { "total": 0.044047117000445724, "count": 1, "is_parallel": true, "self": 0.044047117000445724 }, "steps_from_proto": { "total": 0.0015373449996332056, "count": 1, "is_parallel": true, "self": 0.00032205400111706695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012152909985161386, "count": 8, "is_parallel": true, "self": 0.0012152909985161386 } } } } } } }, "UnityEnvironment.step": { "total": 1182.5441443001328, "count": 63786, "is_parallel": true, "self": 31.584130572083268, "children": { "UnityEnvironment._generate_step_input": { "total": 21.30981762718602, "count": 63786, "is_parallel": true, "self": 21.30981762718602 }, "communicator.exchange": { "total": 1032.174278696879, "count": 63786, "is_parallel": true, "self": 1032.174278696879 }, "steps_from_proto": { "total": 97.47591740398457, "count": 63786, "is_parallel": true, "self": 19.83513641555237, "children": { "_process_rank_one_or_two_observation": { "total": 77.6407809884322, "count": 510288, "is_parallel": true, "self": 77.6407809884322 } } } } } } } } } } }, "trainer_advance": { "total": 629.5185190468173, "count": 63787, "self": 2.290153028901841, "children": { "process_trajectory": { "total": 116.23556688389272, "count": 63787, "self": 116.06141102889342, "children": { "RLTrainer._checkpoint": { "total": 0.17415585499929875, "count": 2, "self": 0.17415585499929875 } } }, "_update_policy": { "total": 510.9927991340228, "count": 450, "self": 285.4047313902356, "children": { "TorchPPOOptimizer.update": { "total": 225.58806774378718, "count": 22743, "self": 225.58806774378718 } } } } } } }, "trainer_threads": { "total": 9.150007826974615e-07, "count": 1, "self": 9.150007826974615e-07 }, "TrainerController._save_models": { "total": 0.07093655900098383, "count": 1, "self": 0.0012961370011908002, "children": { "RLTrainer._checkpoint": { "total": 0.06964042199979303, "count": 1, "self": 0.06964042199979303 } } } } } } }