{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4269441068172455, "min": 0.40471845865249634, "max": 1.4380748271942139, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12931.283203125, "min": 11960.240234375, "max": 43625.4375, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.41870537400245667, "min": -0.10295980423688889, "max": 0.4591412842273712, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 113.88786315917969, "min": -24.813312530517578, "max": 125.8047103881836, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011077631264925003, "min": 0.00532050896435976, "max": 0.43476882576942444, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.013115644454956, "min": 1.4205758571624756, "max": 104.77928924560547, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06854279574638765, "min": 0.06224045026901469, "max": 0.0743986560357314, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9595991404494271, "min": 0.5207905922501198, "max": 1.0656465703505091, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014765559388338479, "min": 0.0008844551964085345, "max": 0.016762815620340127, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2067178314367387, "min": 0.011497917553310949, "max": 0.24424620942947656, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.468533224807143e-06, "min": 7.468533224807143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001045594651473, "min": 0.0001045594651473, "max": 0.003633475688841499, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248947857142857, "min": 0.10248947857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348527, "min": 1.3886848, "max": 2.6111585000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002586989092857143, "min": 0.0002586989092857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036217847300000004, "min": 0.0036217847300000004, "max": 0.12113473415, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012522452510893345, "min": 0.012522452510893345, "max": 0.6186760663986206, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17531433701515198, "min": 0.17531433701515198, "max": 4.330732345581055, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 404.14864864864865, "min": 403.2077922077922, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29907.0, "min": 15984.0, "max": 33284.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3467123073666063, "min": -1.0000000521540642, "max": 1.4668753065846183, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 98.30999843776226, "min": -29.316001757979393, "max": 112.94939860701561, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3467123073666063, "min": -1.0000000521540642, "max": 1.4668753065846183, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 98.30999843776226, "min": -29.316001757979393, "max": 112.94939860701561, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05328998692438951, "min": 0.052140804007455396, "max": 12.719453778117895, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.890169045480434, "min": 3.890169045480434, "max": 203.51126044988632, "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": "1734447565", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1734449831" }, "total": 2266.067674339, "count": 1, "self": 0.7891799949998131, "children": { "run_training.setup": { "total": 0.058102568000094834, "count": 1, "self": 0.058102568000094834 }, "TrainerController.start_learning": { "total": 2265.2203917760003, "count": 1, "self": 1.443237862037222, "children": { "TrainerController._reset_env": { "total": 4.896692443999996, "count": 1, "self": 4.896692443999996 }, "TrainerController.advance": { "total": 2258.749826332963, "count": 63679, "self": 1.5034508619141889, "children": { "env_step": { "total": 1556.3506344399875, "count": 63679, "self": 1398.4827743369478, "children": { "SubprocessEnvManager._take_step": { "total": 156.9896409399837, "count": 63679, "self": 4.725564624965955, "children": { "TorchPolicy.evaluate": { "total": 152.26407631501775, "count": 62553, "self": 152.26407631501775 } } }, "workers": { "total": 0.87821916305586, "count": 63679, "self": 0.0, "children": { "worker_root": { "total": 2259.862507937036, "count": 63679, "is_parallel": true, "self": 981.0707149780533, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002131723000047714, "count": 1, "is_parallel": true, "self": 0.0006994509999458387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014322720001018752, "count": 8, "is_parallel": true, "self": 0.0014322720001018752 } } }, "UnityEnvironment.step": { "total": 0.04946616199993059, "count": 1, "is_parallel": true, "self": 0.0005798119999553819, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046331700002610887, "count": 1, "is_parallel": true, "self": 0.00046331700002610887 }, "communicator.exchange": { "total": 0.04658573099993646, "count": 1, "is_parallel": true, "self": 0.04658573099993646 }, "steps_from_proto": { "total": 0.0018373020000126417, "count": 1, "is_parallel": true, "self": 0.0003771920000872342, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014601099999254075, "count": 8, "is_parallel": true, "self": 0.0014601099999254075 } } } } } } }, "UnityEnvironment.step": { "total": 1278.7917929589826, "count": 63678, "is_parallel": true, "self": 33.38944664296514, "children": { "UnityEnvironment._generate_step_input": { "total": 23.433636013039063, "count": 63678, "is_parallel": true, "self": 23.433636013039063 }, "communicator.exchange": { "total": 1122.3936381330102, "count": 63678, "is_parallel": true, "self": 1122.3936381330102 }, "steps_from_proto": { "total": 99.57507216996828, "count": 63678, "is_parallel": true, "self": 20.465146577818132, "children": { "_process_rank_one_or_two_observation": { "total": 79.10992559215015, "count": 509424, "is_parallel": true, "self": 79.10992559215015 } } } } } } } } } } }, "trainer_advance": { "total": 700.8957410310613, "count": 63679, "self": 2.8488248060617707, "children": { "process_trajectory": { "total": 134.3559044799971, "count": 63679, "self": 134.05160723799725, "children": { "RLTrainer._checkpoint": { "total": 0.30429724199984776, "count": 2, "self": 0.30429724199984776 } } }, "_update_policy": { "total": 563.6910117450025, "count": 453, "self": 320.387032266996, "children": { "TorchPPOOptimizer.update": { "total": 243.30397947800645, "count": 22779, "self": 243.30397947800645 } } } } } } }, "trainer_threads": { "total": 1.264999809791334e-06, "count": 1, "self": 1.264999809791334e-06 }, "TrainerController._save_models": { "total": 0.13063387200008947, "count": 1, "self": 0.002027528999860806, "children": { "RLTrainer._checkpoint": { "total": 0.12860634300022866, "count": 1, "self": 0.12860634300022866 } } } } } } }