{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43124398589134216, "min": 0.3955431878566742, "max": 1.4614990949630737, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12875.220703125, "min": 11992.353515625, "max": 44336.03515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989880.0, "min": 29952.0, "max": 989880.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989880.0, "min": 29952.0, "max": 989880.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.22162096202373505, "min": -0.0918092131614685, "max": 0.22285932302474976, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 56.95658874511719, "min": -21.942401885986328, "max": 56.95658874511719, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0030780162196606398, "min": -0.0030780162196606398, "max": 0.4806993007659912, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.7910501956939697, "min": -0.7910501956939697, "max": 113.92573547363281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06555234380565318, "min": 0.06555234380565318, "max": 0.07402957987652684, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9177328132791445, "min": 0.5024545092860587, "max": 1.094846398711168, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01231775626304928, "min": 0.0005916320509431199, "max": 0.01231775626304928, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17244858768268992, "min": 0.0067553742327361695, "max": 0.17244858768268992, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.633340312728572e-06, "min": 7.633340312728572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010686676437820001, "min": 0.00010686676437820001, "max": 0.0035080322306559994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025444142857143, "min": 0.1025444142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356218000000003, "min": 1.3886848, "max": 2.569344, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026418698714285717, "min": 0.00026418698714285717, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036986178200000006, "min": 0.0036986178200000006, "max": 0.11695746560000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01625346578657627, "min": 0.01625346578657627, "max": 0.5988557934761047, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2275485247373581, "min": 0.2275485247373581, "max": 4.191990375518799, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 580.0566037735849, "min": 580.0566037735849, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30743.0, "min": 15984.0, "max": 32485.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8914678982406292, "min": -1.0000000521540642, "max": 0.921843963265419, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 47.24779860675335, "min": -30.482801668345928, "max": 47.24779860675335, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8914678982406292, "min": -1.0000000521540642, "max": 0.921843963265419, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 47.24779860675335, "min": -30.482801668345928, "max": 47.24779860675335, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09856407713850099, "min": 0.09856407713850099, "max": 12.231072887778282, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.2238960883405525, "min": 4.975898523582146, "max": 195.69716620445251, "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": "1756194021", "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=PyramidTraining --no-graphics", "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": "1756196326" }, "total": 2305.478575574, "count": 1, "self": 0.48331715999984226, "children": { "run_training.setup": { "total": 0.023233363999906942, "count": 1, "self": 0.023233363999906942 }, "TrainerController.start_learning": { "total": 2304.97202505, "count": 1, "self": 1.7317995159551174, "children": { "TrainerController._reset_env": { "total": 3.78912264600001, "count": 1, "self": 3.78912264600001 }, "TrainerController.advance": { "total": 2299.3663940350443, "count": 63341, "self": 1.7410600979910669, "children": { "env_step": { "total": 1600.7298655310628, "count": 63341, "self": 1425.0371003070877, "children": { "SubprocessEnvManager._take_step": { "total": 174.67237272498346, "count": 63341, "self": 5.381487478983445, "children": { "TorchPolicy.evaluate": { "total": 169.29088524600002, "count": 62560, "self": 169.29088524600002 } } }, "workers": { "total": 1.020392498991555, "count": 63341, "self": 0.0, "children": { "worker_root": { "total": 2298.8639346379464, "count": 63341, "is_parallel": true, "self": 1004.537562184928, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007566507000092315, "count": 1, "is_parallel": true, "self": 0.005492876000175784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020736309999165314, "count": 8, "is_parallel": true, "self": 0.0020736309999165314 } } }, "UnityEnvironment.step": { "total": 0.053866833000029146, "count": 1, "is_parallel": true, "self": 0.0006071669999982987, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005220570000119551, "count": 1, "is_parallel": true, "self": 0.0005220570000119551 }, "communicator.exchange": { "total": 0.050911367000026075, "count": 1, "is_parallel": true, "self": 0.050911367000026075 }, "steps_from_proto": { "total": 0.001826241999992817, "count": 1, "is_parallel": true, "self": 0.0003880630000594465, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014381789999333705, "count": 8, "is_parallel": true, "self": 0.0014381789999333705 } } } } } } }, "UnityEnvironment.step": { "total": 1294.3263724530184, "count": 63340, "is_parallel": true, "self": 35.23027520702749, "children": { "UnityEnvironment._generate_step_input": { "total": 25.139718946025255, "count": 63340, "is_parallel": true, "self": 25.139718946025255 }, "communicator.exchange": { "total": 1126.2381694849978, "count": 63340, "is_parallel": true, "self": 1126.2381694849978 }, "steps_from_proto": { "total": 107.71820881496774, "count": 63340, "is_parallel": true, "self": 22.350479007951208, "children": { "_process_rank_one_or_two_observation": { "total": 85.36772980701653, "count": 506720, "is_parallel": true, "self": 85.36772980701653 } } } } } } } } } } }, "trainer_advance": { "total": 696.8954684059905, "count": 63341, "self": 3.341401394933655, "children": { "process_trajectory": { "total": 135.34874582106045, "count": 63341, "self": 135.06540600206017, "children": { "RLTrainer._checkpoint": { "total": 0.2833398190002754, "count": 2, "self": 0.2833398190002754 } } }, "_update_policy": { "total": 558.2053211899964, "count": 447, "self": 307.47897516396984, "children": { "TorchPPOOptimizer.update": { "total": 250.7263460260266, "count": 22782, "self": 250.7263460260266 } } } } } } }, "trainer_threads": { "total": 9.630002750782296e-07, "count": 1, "self": 9.630002750782296e-07 }, "TrainerController._save_models": { "total": 0.08470789000011791, "count": 1, "self": 0.001316566000241437, "children": { "RLTrainer._checkpoint": { "total": 0.08339132399987648, "count": 1, "self": 0.08339132399987648 } } } } } } }