{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3651166260242462, "min": 0.3608821928501129, "max": 1.3695505857467651, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10900.921875, "min": 10786.046875, "max": 41546.6875, "count": 33 }, "Pyramids.Step.mean": { "value": 989894.0, "min": 29952.0, "max": 989894.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989894.0, "min": 29952.0, "max": 989894.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5155501365661621, "min": -0.09626627713441849, "max": 0.5155501365661621, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.29183959960938, "min": -23.200172424316406, "max": 142.29183959960938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0607370100915432, "min": -0.001480317790992558, "max": 0.28856512904167175, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 16.76341438293457, "min": -0.40412676334381104, "max": 68.38993835449219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06929886969539881, "min": 0.06557410082395687, "max": 0.07288827609592603, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.039483045430982, "min": 0.4998808911270275, "max": 1.0796724683217083, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01882953189582194, "min": 0.0008484220679350801, "max": 0.01882953189582194, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.28244297843732913, "min": 0.011029486883156041, "max": 0.28244297843732913, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.503737498786665e-06, "min": 7.503737498786665e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011255606248179998, "min": 0.00011255606248179998, "max": 0.0034920445359851995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250121333333335, "min": 0.10250121333333335, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375182000000003, "min": 1.3886848, "max": 2.4844308, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002598712119999999, "min": 0.0002598712119999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003898068179999999, "min": 0.003898068179999999, "max": 0.11641507851999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01265661045908928, "min": 0.01265661045908928, "max": 0.37260934710502625, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1898491531610489, "min": 0.1787531077861786, "max": 2.6082653999328613, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 354.03409090909093, "min": 354.03409090909093, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31155.0, "min": 15984.0, "max": 32557.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5550204303792932, "min": -1.0000000521540642, "max": 1.6069466485579809, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 136.8417978733778, "min": -29.900401651859283, "max": 136.8417978733778, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5550204303792932, "min": -1.0000000521540642, "max": 1.6069466485579809, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 136.8417978733778, "min": -29.900401651859283, "max": 136.8417978733778, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04594229746064891, "min": 0.04594229746064891, "max": 7.262736681848764, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.042922176537104, "min": 3.9215699458291056, "max": 116.20378690958023, "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": "1744989510", "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": "1744991700" }, "total": 2189.966281991, "count": 1, "self": 0.5256454299997131, "children": { "run_training.setup": { "total": 0.02665208299981714, "count": 1, "self": 0.02665208299981714 }, "TrainerController.start_learning": { "total": 2189.413984478, "count": 1, "self": 1.3017614999539546, "children": { "TrainerController._reset_env": { "total": 2.387907185000131, "count": 1, "self": 2.387907185000131 }, "TrainerController.advance": { "total": 2185.638409426046, "count": 63751, "self": 1.3602942540487675, "children": { "env_step": { "total": 1508.624126571982, "count": 63751, "self": 1357.4692683489918, "children": { "SubprocessEnvManager._take_step": { "total": 150.37141926007644, "count": 63751, "self": 4.573715827077422, "children": { "TorchPolicy.evaluate": { "total": 145.79770343299901, "count": 62567, "self": 145.79770343299901 } } }, "workers": { "total": 0.7834389629138059, "count": 63751, "self": 0.0, "children": { "worker_root": { "total": 2184.572294985995, "count": 63751, "is_parallel": true, "self": 936.5382090979394, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019488479999836272, "count": 1, "is_parallel": true, "self": 0.0006132820001312211, "children": { "_process_rank_one_or_two_observation": { "total": 0.001335565999852406, "count": 8, "is_parallel": true, "self": 0.001335565999852406 } } }, "UnityEnvironment.step": { "total": 0.0508549609999136, "count": 1, "is_parallel": true, "self": 0.0005144369999925402, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000443738000058147, "count": 1, "is_parallel": true, "self": 0.000443738000058147 }, "communicator.exchange": { "total": 0.048254510999868216, "count": 1, "is_parallel": true, "self": 0.048254510999868216 }, "steps_from_proto": { "total": 0.0016422749999946973, "count": 1, "is_parallel": true, "self": 0.0003779139999551262, "children": { "_process_rank_one_or_two_observation": { "total": 0.001264361000039571, "count": 8, "is_parallel": true, "self": 0.001264361000039571 } } } } } } }, "UnityEnvironment.step": { "total": 1248.0340858880556, "count": 63750, "is_parallel": true, "self": 31.30718234704841, "children": { "UnityEnvironment._generate_step_input": { "total": 22.61192516493975, "count": 63750, "is_parallel": true, "self": 22.61192516493975 }, "communicator.exchange": { "total": 1101.2227471300316, "count": 63750, "is_parallel": true, "self": 1101.2227471300316 }, "steps_from_proto": { "total": 92.89223124603586, "count": 63750, "is_parallel": true, "self": 18.262065221020066, "children": { "_process_rank_one_or_two_observation": { "total": 74.6301660250158, "count": 510000, "is_parallel": true, "self": 74.6301660250158 } } } } } } } } } } }, "trainer_advance": { "total": 675.6539886000153, "count": 63751, "self": 2.5251939879938163, "children": { "process_trajectory": { "total": 126.72986136701525, "count": 63751, "self": 126.53334936801525, "children": { "RLTrainer._checkpoint": { "total": 0.19651199899999483, "count": 2, "self": 0.19651199899999483 } } }, "_update_policy": { "total": 546.3989332450062, "count": 450, "self": 300.2965555399792, "children": { "TorchPPOOptimizer.update": { "total": 246.10237770502704, "count": 22764, "self": 246.10237770502704 } } } } } } }, "trainer_threads": { "total": 1.2040000001434237e-06, "count": 1, "self": 1.2040000001434237e-06 }, "TrainerController._save_models": { "total": 0.08590516300000672, "count": 1, "self": 0.0013538380003410566, "children": { "RLTrainer._checkpoint": { "total": 0.08455132499966567, "count": 1, "self": 0.08455132499966567 } } } } } } }