{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9082182049751282, "min": 0.87479168176651, "max": 1.6093244552612305, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 1860.0308837890625, "min": 797.4410400390625, "max": 3295.896484375, "count": 50 }, "Pyramids.Step.mean": { "value": 99965.0, "min": 1920.0, "max": 99965.0, "count": 50 }, "Pyramids.Step.sum": { "value": 99965.0, "min": 1920.0, "max": 99965.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07558449357748032, "min": -0.10592581331729889, "max": 0.12113308906555176, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -1.209351897239685, "min": -1.680419683456421, "max": 1.9381294250488281, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.09358764439821243, "min": -0.14957760274410248, "max": 0.2111683189868927, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.497402310371399, "min": -2.3932416439056396, "max": 3.378693103790283, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06861115565767423, "min": 0.05883824355343635, "max": 0.08491418677537392, "count": 31 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.06861115565767423, "min": 0.05883824355343635, "max": 0.08491418677537392, "count": 31 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00031524660586174357, "min": 0.0002118563619054233, "max": 0.025657440661840763, "count": 31 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.00031524660586174357, "min": 0.0002118563619054233, "max": 0.025657440661840763, "count": 31 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.89099837000006e-07, "min": 4.89099837000006e-07, "max": 0.00028771200409599993, "count": 31 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.89099837000006e-07, "min": 4.89099837000006e-07, "max": 0.00028771200409599993, "count": 31 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10016300000000002, "min": 0.10016300000000002, "max": 0.19590400000000005, "count": 31 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.10016300000000002, "min": 0.10016300000000002, "max": 0.19590400000000005, "count": 31 }, "Pyramids.Policy.Beta.mean": { "value": 2.6283700000000194e-05, "min": 2.6283700000000194e-05, "max": 0.0095908096, "count": 31 }, "Pyramids.Policy.Beta.sum": { "value": 2.6283700000000194e-05, "min": 2.6283700000000194e-05, "max": 0.0095908096, "count": 31 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.06737803667783737, "min": 0.06737803667783737, "max": 0.7952181696891785, "count": 31 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06737803667783737, "min": 0.06737803667783737, "max": 0.7952181696891785, "count": 31 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 996.7142857142857, "min": 744.0, "max": 999.0, "count": 12 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 13954.0, "min": 744.0, "max": 15984.0, "count": 12 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8547286210315568, "min": -1.0000000521540642, "max": 1.2559999972581863, "count": 15 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -11.966200694441795, "min": -15.000000782310963, "max": 1.2559999972581863, "count": 15 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8547286210315568, "min": -1.0000000521540642, "max": 1.2559999972581863, "count": 15 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -11.966200694441795, "min": -15.000000782310963, "max": 1.2559999972581863, "count": 15 }, "Pyramids.Policy.RndReward.mean": { "value": 0.775420717895031, "min": 0.7220818847417831, "max": 6.420726441343626, "count": 15 }, "Pyramids.Policy.RndReward.sum": { "value": 10.855890050530434, "min": 0.7220818847417831, "max": 96.31089662015438, "count": 15 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1790098312", "python_version": "3.10.12 (main, Jul 26 2023, 19:37:41) [Clang 16.0.3 ]", "command_line_arguments": "./.venv-mla/bin/mlagents-learn ./config/Pyramids_run.yaml --env=./envs/Startup/Startup.app --run-id=Pyramids2 --results-dir=./results --no-graphics --base-port=6080 --force --env-args --mlagents-scene-name Assets/ML-Agents/Examples/Pyramids/Scenes/Pyramids.unity", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1", "numpy_version": "1.23.5", "end_time_seconds": "1790100893" }, "total": 2580.962755958026, "count": 1, "self": 0.9887815830297768, "children": { "run_training.setup": { "total": 0.14984104200266302, "count": 1, "self": 0.14984104200266302 }, "TrainerController.start_learning": { "total": 2579.8241333329934, "count": 1, "self": 0.25993692729389295, "children": { "TrainerController._reset_env": { "total": 7.088897333014756, "count": 1, "self": 7.088897333014756 }, "TrainerController.advance": { "total": 2572.3850559476414, "count": 6337, "self": 0.28941082960227504, "children": { "env_step": { "total": 2046.8436690266826, "count": 6337, "self": 1975.1657304082182, "children": { "SubprocessEnvManager._take_step": { "total": 71.30303015460959, "count": 6337, "self": 2.3501474938821048, "children": { "TorchPolicy.evaluate": { "total": 68.95288266072748, "count": 6331, "self": 68.95288266072748 } } }, "workers": { "total": 0.37490846385480836, "count": 6337, "self": 0.0, "children": { "worker_root": { "total": 2573.1003180179396, "count": 6337, "is_parallel": true, "self": 626.1661453726701, "children": { "steps_from_proto": { "total": 0.0007749159703962505, "count": 1, "is_parallel": true, "self": 0.00017699989257380366, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005979160778224468, "count": 8, "is_parallel": true, "self": 0.0005979160778224468 } } }, "UnityEnvironment.step": { "total": 1946.933397729299, "count": 6337, "is_parallel": true, "self": 1.5140102336881682, "children": { "UnityEnvironment._generate_step_input": { "total": 4.4776417510584, "count": 6337, "is_parallel": true, "self": 4.4776417510584 }, "communicator.exchange": { "total": 1932.070827980293, "count": 6337, "is_parallel": true, "self": 1932.070827980293 }, "steps_from_proto": { "total": 8.870917764259502, "count": 6337, "is_parallel": true, "self": 1.8004718804731965, "children": { "_process_rank_one_or_two_observation": { "total": 7.070445883786306, "count": 50696, "is_parallel": true, "self": 7.070445883786306 } } } } } } } } } } }, "trainer_advance": { "total": 525.2519760913565, "count": 6337, "self": 0.3286859543877654, "children": { "process_trajectory": { "total": 39.73427055275533, "count": 6337, "self": 39.73427055275533 }, "_update_policy": { "total": 485.1890195842134, "count": 31, "self": 47.87891324906377, "children": { "TorchPPOOptimizer.update": { "total": 437.3101063351496, "count": 2325, "self": 437.3101063351496 } } } } } } }, "trainer_threads": { "total": 1.2500095181167126e-06, "count": 1, "self": 1.2500095181167126e-06 }, "TrainerController._save_models": { "total": 0.09024187503382564, "count": 1, "self": 0.0024025000166147947, "children": { "RLTrainer._checkpoint": { "total": 0.08783937501721084, "count": 1, "self": 0.08783937501721084 } } } } } } }