{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3212706446647644, "min": 0.3212706446647644, "max": 1.5096741914749146, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9550.7333984375, "min": 9550.7333984375, "max": 45797.4765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6312903761863708, "min": -0.16419419646263123, "max": 0.6736616492271423, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.13002014160156, "min": -38.914024353027344, "max": 191.9935760498047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015564392320811749, "min": -0.004267923068255186, "max": 0.29681316018104553, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.342465400695801, "min": -1.1608750820159912, "max": 71.53197479248047, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0682397596253958, "min": 0.06557243978576957, "max": 0.07390170244518487, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9553566347555412, "min": 0.5173119171162941, "max": 1.0963641298962208, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01397342407868941, "min": 0.0011464143628346136, "max": 0.015867200412968588, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19562793710165174, "min": 0.013756972354015363, "max": 0.2380080061945288, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.401868961314286e-06, "min": 7.401868961314286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001036261654584, "min": 0.0001036261654584, "max": 0.0033834002721999995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246725714285713, "min": 0.10246725714285713, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345416, "min": 1.3886848, "max": 2.5278, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002564789885714286, "min": 0.0002564789885714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00359070584, "min": 0.00359070584, "max": 0.11280722, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009490794502198696, "min": 0.009490794502198696, "max": 0.42878207564353943, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1328711211681366, "min": 0.1328711211681366, "max": 3.001474618911743, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 325.3440860215054, "min": 274.99056603773585, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30257.0, "min": 15984.0, "max": 32668.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6736956322970598, "min": -1.0000000521540642, "max": 1.681734635835827, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.9799981713295, "min": -30.99680159986019, "max": 178.47839824855328, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6736956322970598, "min": -1.0000000521540642, "max": 1.681734635835827, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.9799981713295, "min": -30.99680159986019, "max": 178.47839824855328, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03206343422299023, "min": 0.028250009673386464, "max": 8.413440052419901, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9498359485151013, "min": 2.9498359485151013, "max": 134.61504083871841, "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": "1724940279", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids3 --no-graphics", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1724942822" }, "total": 2542.9706848959995, "count": 1, "self": 0.5320955819997835, "children": { "run_training.setup": { "total": 0.08044538800004375, "count": 1, "self": 0.08044538800004375 }, "TrainerController.start_learning": { "total": 2542.3581439259997, "count": 1, "self": 2.014526585981457, "children": { "TrainerController._reset_env": { "total": 2.3941783719997147, "count": 1, "self": 2.3941783719997147 }, "TrainerController.advance": { "total": 2537.862395350019, "count": 64019, "self": 1.9511561571130187, "children": { "env_step": { "total": 1813.5757900169124, "count": 64019, "self": 1649.6543028220572, "children": { "SubprocessEnvManager._take_step": { "total": 162.7489851848527, "count": 64019, "self": 5.96284653487146, "children": { "TorchPolicy.evaluate": { "total": 156.78613864998124, "count": 62564, "self": 156.78613864998124 } } }, "workers": { "total": 1.1725020100025176, "count": 64019, "self": 0.0, "children": { "worker_root": { "total": 2535.9339761719843, "count": 64019, "is_parallel": true, "self": 1026.545629238014, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029493209999600367, "count": 1, "is_parallel": true, "self": 0.0008297760000459675, "children": { "_process_rank_one_or_two_observation": { "total": 0.002119544999914069, "count": 8, "is_parallel": true, "self": 0.002119544999914069 } } }, "UnityEnvironment.step": { "total": 0.054921843000101944, "count": 1, "is_parallel": true, "self": 0.0005929150001975358, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005381959999795072, "count": 1, "is_parallel": true, "self": 0.0005381959999795072 }, "communicator.exchange": { "total": 0.05183892300010484, "count": 1, "is_parallel": true, "self": 0.05183892300010484 }, "steps_from_proto": { "total": 0.0019518089998200594, "count": 1, "is_parallel": true, "self": 0.0004128480004510493, "children": { "_process_rank_one_or_two_observation": { "total": 0.00153896099936901, "count": 8, "is_parallel": true, "self": 0.00153896099936901 } } } } } } }, "UnityEnvironment.step": { "total": 1509.3883469339703, "count": 64018, "is_parallel": true, "self": 38.70039026799486, "children": { "UnityEnvironment._generate_step_input": { "total": 27.872592083902873, "count": 64018, "is_parallel": true, "self": 27.872592083902873 }, "communicator.exchange": { "total": 1313.9751875549614, "count": 64018, "is_parallel": true, "self": 1313.9751875549614 }, "steps_from_proto": { "total": 128.84017702711117, "count": 64018, "is_parallel": true, "self": 26.545686797984672, "children": { "_process_rank_one_or_two_observation": { "total": 102.2944902291265, "count": 512144, "is_parallel": true, "self": 102.2944902291265 } } } } } } } } } } }, "trainer_advance": { "total": 722.3354491759937, "count": 64019, "self": 3.561608478996277, "children": { "process_trajectory": { "total": 139.56324720199927, "count": 64019, "self": 139.35028932899968, "children": { "RLTrainer._checkpoint": { "total": 0.21295787299959557, "count": 2, "self": 0.21295787299959557 } } }, "_update_policy": { "total": 579.2105934949982, "count": 452, "self": 364.71019310702286, "children": { "TorchPPOOptimizer.update": { "total": 214.50040038797533, "count": 22821, "self": 214.50040038797533 } } } } } } }, "trainer_threads": { "total": 1.0859994290512986e-06, "count": 1, "self": 1.0859994290512986e-06 }, "TrainerController._save_models": { "total": 0.08704253199994127, "count": 1, "self": 0.0014544270006808802, "children": { "RLTrainer._checkpoint": { "total": 0.0855881049992604, "count": 1, "self": 0.0855881049992604 } } } } } } }