{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42411768436431885, "min": 0.42411768436431885, "max": 1.487685203552246, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12553.8837890625, "min": 12553.8837890625, "max": 45130.41796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989888.0, "min": 29952.0, "max": 989888.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989888.0, "min": 29952.0, "max": 989888.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5534465909004211, "min": -0.10796164721250534, "max": 0.6020606756210327, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 151.6443634033203, "min": -26.018756866455078, "max": 170.3831787109375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02039172686636448, "min": -0.00856967642903328, "max": 0.41094210743904114, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.5873332023620605, "min": -2.3052430152893066, "max": 97.39328002929688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07005225118094434, "min": 0.06527260991528498, "max": 0.07325448892039152, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9807315165332208, "min": 0.5127814224427406, "max": 1.0616215749178082, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01412556606824399, "min": 0.00034655866457363, "max": 0.01752259915041022, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19775792495541586, "min": 0.004505262639457191, "max": 0.24531638810574308, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.739711705842856e-06, "min": 7.739711705842856e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010835596388179998, "min": 0.00010835596388179998, "max": 0.0036087837970721, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257987142857143, "min": 0.10257987142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361182000000001, "min": 1.3886848, "max": 2.5696646000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002677291557142858, "min": 0.0002677291557142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037482081800000013, "min": 0.0037482081800000013, "max": 0.12030249721, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008206339552998543, "min": 0.008206339552998543, "max": 0.4939265847206116, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1148887574672699, "min": 0.1148887574672699, "max": 3.457486152648926, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 345.43373493975906, "min": 316.36170212765956, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28671.0, "min": 15984.0, "max": 32850.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5827214067713136, "min": -1.0000000521540642, "max": 1.6836382776815841, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.94859816879034, "min": -30.994001604616642, "max": 158.2619981020689, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5827214067713136, "min": -1.0000000521540642, "max": 1.6836382776815841, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.94859816879034, "min": -30.994001604616642, "max": 158.2619981020689, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029758985963694397, "min": 0.029758985963694397, "max": 10.729716904461384, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4997548209503293, "min": 2.4997548209503293, "max": 171.67547047138214, "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": "1693716773", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1693719027" }, "total": 2253.858343441, "count": 1, "self": 0.8893848950006031, "children": { "run_training.setup": { "total": 0.04274361699998508, "count": 1, "self": 0.04274361699998508 }, "TrainerController.start_learning": { "total": 2252.926214929, "count": 1, "self": 1.4359639500012236, "children": { "TrainerController._reset_env": { "total": 4.378243999000006, "count": 1, "self": 4.378243999000006 }, "TrainerController.advance": { "total": 2246.9563217229984, "count": 63925, "self": 1.4033679249514535, "children": { "env_step": { "total": 1582.6366164500002, "count": 63925, "self": 1470.9390388839538, "children": { "SubprocessEnvManager._take_step": { "total": 110.82413800700482, "count": 63925, "self": 4.800968192968753, "children": { "TorchPolicy.evaluate": { "total": 106.02316981403607, "count": 62563, "self": 106.02316981403607 } } }, "workers": { "total": 0.8734395590415147, "count": 63925, "self": 0.0, "children": { "worker_root": { "total": 2247.7991108599863, "count": 63925, "is_parallel": true, "self": 893.0206526419863, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0051559010000232774, "count": 1, "is_parallel": true, "self": 0.0037342860001103872, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014216149999128902, "count": 8, "is_parallel": true, "self": 0.0014216149999128902 } } }, "UnityEnvironment.step": { "total": 0.05092274499997984, "count": 1, "is_parallel": true, "self": 0.001850885999942875, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005013289999737935, "count": 1, "is_parallel": true, "self": 0.0005013289999737935 }, "communicator.exchange": { "total": 0.04663789300002463, "count": 1, "is_parallel": true, "self": 0.04663789300002463 }, "steps_from_proto": { "total": 0.0019326370000385396, "count": 1, "is_parallel": true, "self": 0.00039419900002712893, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015384380000114106, "count": 8, "is_parallel": true, "self": 0.0015384380000114106 } } } } } } }, "UnityEnvironment.step": { "total": 1354.778458218, "count": 63924, "is_parallel": true, "self": 35.83692390604233, "children": { "UnityEnvironment._generate_step_input": { "total": 23.48403979396852, "count": 63924, "is_parallel": true, "self": 23.48403979396852 }, "communicator.exchange": { "total": 1186.9518569100057, "count": 63924, "is_parallel": true, "self": 1186.9518569100057 }, "steps_from_proto": { "total": 108.50563760798343, "count": 63924, "is_parallel": true, "self": 21.225185424160145, "children": { "_process_rank_one_or_two_observation": { "total": 87.28045218382329, "count": 511392, "is_parallel": true, "self": 87.28045218382329 } } } } } } } } } } }, "trainer_advance": { "total": 662.9163373480468, "count": 63925, "self": 2.6964684920220634, "children": { "process_trajectory": { "total": 112.64964723902625, "count": 63925, "self": 112.27691896402615, "children": { "RLTrainer._checkpoint": { "total": 0.37272827500009953, "count": 2, "self": 0.37272827500009953 } } }, "_update_policy": { "total": 547.5702216169984, "count": 453, "self": 358.54527271602103, "children": { "TorchPPOOptimizer.update": { "total": 189.0249489009774, "count": 22776, "self": 189.0249489009774 } } } } } } }, "trainer_threads": { "total": 1.395000253978651e-06, "count": 1, "self": 1.395000253978651e-06 }, "TrainerController._save_models": { "total": 0.15568386199993256, "count": 1, "self": 0.0018303540000488283, "children": { "RLTrainer._checkpoint": { "total": 0.15385350799988373, "count": 1, "self": 0.15385350799988373 } } } } } } }