{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47819089889526367, "min": 0.47819089889526367, "max": 1.363081693649292, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14322.7734375, "min": 14322.7734375, "max": 41350.4453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989935.0, "min": 29952.0, "max": 989935.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989935.0, "min": 29952.0, "max": 989935.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.39008432626724243, "min": -0.0817650705575943, "max": 0.39008432626724243, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 104.93268585205078, "min": -19.705381393432617, "max": 104.93268585205078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.45236068964004517, "min": -0.016804542392492294, "max": 0.6269820928573608, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 121.68502807617188, "min": -4.385985374450684, "max": 148.59475708007812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07055233336211619, "min": 0.06553941779739468, "max": 0.07339595149985484, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9877326670696267, "min": 0.5122514191234482, "max": 1.0495398727750096, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.05143785007163153, "min": 0.0007779790039364318, "max": 0.05143785007163153, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.7201299010028414, "min": 0.010891706055110046, "max": 0.7201299010028414, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.445647518149998e-06, "min": 7.445647518149998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010423906525409996, "min": 0.00010423906525409996, "max": 0.003509348930217099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248184999999999, "min": 0.10248184999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347458999999998, "min": 1.3886848, "max": 2.5697829000000008, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025793681499999995, "min": 0.00025793681499999995, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003611115409999999, "min": 0.003611115409999999, "max": 0.11700131170999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013566105626523495, "min": 0.013566105626523495, "max": 0.596741795539856, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18992547690868378, "min": 0.18992547690868378, "max": 4.177192687988281, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 424.1641791044776, "min": 424.1641791044776, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28419.0, "min": 15984.0, "max": 33635.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3966895262919254, "min": -1.0000000521540642, "max": 1.3966895262919254, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 93.57819826155901, "min": -30.473401717841625, "max": 93.57819826155901, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3966895262919254, "min": -1.0000000521540642, "max": 1.3966895262919254, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 93.57819826155901, "min": -30.473401717841625, "max": 93.57819826155901, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.060209260731779124, "min": 0.060209260731779124, "max": 13.33237960189581, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.034020469029201, "min": 3.955770336848218, "max": 213.31807363033295, "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": "1750231730", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750233806" }, "total": 2076.1654329519997, "count": 1, "self": 0.48652922800010856, "children": { "run_training.setup": { "total": 0.022851544999866746, "count": 1, "self": 0.022851544999866746 }, "TrainerController.start_learning": { "total": 2075.6560521789997, "count": 1, "self": 1.265779956847382, "children": { "TrainerController._reset_env": { "total": 2.15278812500037, "count": 1, "self": 2.15278812500037 }, "TrainerController.advance": { "total": 2072.1548041361525, "count": 63532, "self": 1.3365034721887241, "children": { "env_step": { "total": 1423.564247565967, "count": 63532, "self": 1279.4751288259286, "children": { "SubprocessEnvManager._take_step": { "total": 143.33280665999655, "count": 63532, "self": 4.427494232020763, "children": { "TorchPolicy.evaluate": { "total": 138.9053124279758, "count": 62561, "self": 138.9053124279758 } } }, "workers": { "total": 0.7563120800418801, "count": 63532, "self": 0.0, "children": { "worker_root": { "total": 2070.766428641044, "count": 63532, "is_parallel": true, "self": 899.4045845030673, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019373840000298514, "count": 1, "is_parallel": true, "self": 0.000695755999913672, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012416280001161795, "count": 8, "is_parallel": true, "self": 0.0012416280001161795 } } }, "UnityEnvironment.step": { "total": 0.04554941200012763, "count": 1, "is_parallel": true, "self": 0.0005152459998498671, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005011799999010691, "count": 1, "is_parallel": true, "self": 0.0005011799999010691 }, "communicator.exchange": { "total": 0.04293880400018679, "count": 1, "is_parallel": true, "self": 0.04293880400018679 }, "steps_from_proto": { "total": 0.0015941820001899032, "count": 1, "is_parallel": true, "self": 0.0003198730000804062, "children": { "_process_rank_one_or_two_observation": { "total": 0.001274309000109497, "count": 8, "is_parallel": true, "self": 0.001274309000109497 } } } } } } }, "UnityEnvironment.step": { "total": 1171.3618441379767, "count": 63531, "is_parallel": true, "self": 31.24904059883511, "children": { "UnityEnvironment._generate_step_input": { "total": 22.832585946064228, "count": 63531, "is_parallel": true, "self": 22.832585946064228 }, "communicator.exchange": { "total": 1022.6993104411135, "count": 63531, "is_parallel": true, "self": 1022.6993104411135 }, "steps_from_proto": { "total": 94.58090715196386, "count": 63531, "is_parallel": true, "self": 18.928059840918195, "children": { "_process_rank_one_or_two_observation": { "total": 75.65284731104566, "count": 508248, "is_parallel": true, "self": 75.65284731104566 } } } } } } } } } } }, "trainer_advance": { "total": 647.2540530979968, "count": 63532, "self": 2.5117015530245226, "children": { "process_trajectory": { "total": 123.02967288697073, "count": 63532, "self": 122.70737630597068, "children": { "RLTrainer._checkpoint": { "total": 0.322296581000046, "count": 2, "self": 0.322296581000046 } } }, "_update_policy": { "total": 521.7126786580016, "count": 453, "self": 292.6286107329888, "children": { "TorchPPOOptimizer.update": { "total": 229.08406792501273, "count": 22773, "self": 229.08406792501273 } } } } } } }, "trainer_threads": { "total": 9.309997039963491e-07, "count": 1, "self": 9.309997039963491e-07 }, "TrainerController._save_models": { "total": 0.08267902999978105, "count": 1, "self": 0.00110427100025845, "children": { "RLTrainer._checkpoint": { "total": 0.0815747589995226, "count": 1, "self": 0.0815747589995226 } } } } } } }