{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4847096800804138, "min": 0.46653735637664795, "max": 1.4601467847824097, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14502.513671875, "min": 13966.2626953125, "max": 44295.01171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989964.0, "min": 29952.0, "max": 989964.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989964.0, "min": 29952.0, "max": 989964.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1252206414937973, "min": -0.10299812257289886, "max": 0.15921834111213684, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 31.43037986755371, "min": -24.822547912597656, "max": 40.12302017211914, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005594240035861731, "min": -0.00724094407632947, "max": 0.3427627682685852, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4041543006896973, "min": -1.8102359771728516, "max": 81.23477935791016, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07184295480191293, "min": 0.06533377064103373, "max": 0.0738250105108212, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.077644322028694, "min": 0.47667058811177787, "max": 1.077644322028694, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00940623532268445, "min": 0.00012526080969339925, "max": 0.014668392195239896, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14109352984026674, "min": 0.00162839052601419, "max": 0.14109352984026674, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.43491752172667e-06, "min": 7.43491752172667e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011152376282590004, "min": 0.00011152376282590004, "max": 0.0031367948544017994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247827333333336, "min": 0.10247827333333336, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371741000000003, "min": 1.3691136000000002, "max": 2.4435580000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025757950600000006, "min": 0.00025757950600000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038636925900000013, "min": 0.0038636925900000013, "max": 0.10458526018000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00657698605209589, "min": 0.00657698605209589, "max": 0.517527163028717, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09865479171276093, "min": 0.0958457887172699, "max": 3.622690200805664, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 679.2, "min": 679.2, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30564.0, "min": 15984.0, "max": 32377.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.520542184346252, "min": -1.0000000521540642, "max": 0.520542184346252, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 23.42439829558134, "min": -32.000001668930054, "max": 23.42439829558134, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.520542184346252, "min": -1.0000000521540642, "max": 0.520542184346252, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 23.42439829558134, "min": -32.000001668930054, "max": 23.42439829558134, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047264640302617206, "min": 0.047264640302617206, "max": 11.028586469590664, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1269088136177743, "min": 2.0501779096666723, "max": 176.45738351345062, "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": "1742841161", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742843624" }, "total": 2463.127621471, "count": 1, "self": 0.4773878609998974, "children": { "run_training.setup": { "total": 0.03236518199992133, "count": 1, "self": 0.03236518199992133 }, "TrainerController.start_learning": { "total": 2462.6178684280003, "count": 1, "self": 1.8110850909538385, "children": { "TrainerController._reset_env": { "total": 2.969214313999828, "count": 1, "self": 2.969214313999828 }, "TrainerController.advance": { "total": 2457.736359339047, "count": 63277, "self": 1.8236922660958044, "children": { "env_step": { "total": 1686.2510285079898, "count": 63277, "self": 1493.418697969987, "children": { "SubprocessEnvManager._take_step": { "total": 191.78908464103188, "count": 63277, "self": 5.594146105048367, "children": { "TorchPolicy.evaluate": { "total": 186.1949385359835, "count": 62571, "self": 186.1949385359835 } } }, "workers": { "total": 1.0432458969708023, "count": 63277, "self": 0.0, "children": { "worker_root": { "total": 2456.789050299968, "count": 63277, "is_parallel": true, "self": 1100.9937586339079, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004023516999950516, "count": 1, "is_parallel": true, "self": 0.0014513099995383527, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025722070004121633, "count": 8, "is_parallel": true, "self": 0.0025722070004121633 } } }, "UnityEnvironment.step": { "total": 0.05513158099984139, "count": 1, "is_parallel": true, "self": 0.0006038229998921452, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005018900001232396, "count": 1, "is_parallel": true, "self": 0.0005018900001232396 }, "communicator.exchange": { "total": 0.05207881299998007, "count": 1, "is_parallel": true, "self": 0.05207881299998007 }, "steps_from_proto": { "total": 0.0019470549998459319, "count": 1, "is_parallel": true, "self": 0.0004085319994828751, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015385230003630568, "count": 8, "is_parallel": true, "self": 0.0015385230003630568 } } } } } } }, "UnityEnvironment.step": { "total": 1355.7952916660602, "count": 63276, "is_parallel": true, "self": 37.29202799700556, "children": { "UnityEnvironment._generate_step_input": { "total": 27.97431511197101, "count": 63276, "is_parallel": true, "self": 27.97431511197101 }, "communicator.exchange": { "total": 1174.8277466860347, "count": 63276, "is_parallel": true, "self": 1174.8277466860347 }, "steps_from_proto": { "total": 115.70120187104885, "count": 63276, "is_parallel": true, "self": 24.307458746011207, "children": { "_process_rank_one_or_two_observation": { "total": 91.39374312503764, "count": 506208, "is_parallel": true, "self": 91.39374312503764 } } } } } } } } } } }, "trainer_advance": { "total": 769.6616385649613, "count": 63277, "self": 3.207955299908008, "children": { "process_trajectory": { "total": 146.1378363480544, "count": 63277, "self": 145.90893373305425, "children": { "RLTrainer._checkpoint": { "total": 0.22890261500015185, "count": 2, "self": 0.22890261500015185 } } }, "_update_policy": { "total": 620.3158469169989, "count": 435, "self": 340.43439565998506, "children": { "TorchPPOOptimizer.update": { "total": 279.88145125701385, "count": 22782, "self": 279.88145125701385 } } } } } } }, "trainer_threads": { "total": 1.1269999049545731e-06, "count": 1, "self": 1.1269999049545731e-06 }, "TrainerController._save_models": { "total": 0.10120855700006359, "count": 1, "self": 0.0017361909999635827, "children": { "RLTrainer._checkpoint": { "total": 0.09947236600010001, "count": 1, "self": 0.09947236600010001 } } } } } } }