{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3810097575187683, "min": 0.3765993118286133, "max": 1.4579148292541504, "count": 35 }, "Pyramids.Policy.Entropy.sum": { "value": 11412.00390625, "min": 11213.62109375, "max": 44227.3046875, "count": 35 }, "Pyramids.Step.mean": { "value": 1049957.0, "min": 29952.0, "max": 1049957.0, "count": 35 }, "Pyramids.Step.sum": { "value": 1049957.0, "min": 29952.0, "max": 1049957.0, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5101847052574158, "min": -0.0890505313873291, "max": 0.6772024035453796, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 141.3211669921875, "min": -21.461177825927734, "max": 200.451904296875, "count": 35 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.024225585162639618, "min": 0.011643638834357262, "max": 0.47462204098701477, "count": 35 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.710486888885498, "min": 3.190356969833374, "max": 112.48542022705078, "count": 35 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07328553975485422, "min": 0.06415854907494838, "max": 0.0740847149169935, "count": 35 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.025997556567959, "min": 0.5185930044189545, "max": 1.046354082837591, "count": 35 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015438001801030572, "min": 0.0006301064794834626, "max": 0.01850804047049571, "count": 35 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.216132025214428, "min": 0.006931171274318088, "max": 0.27762060705743563, "count": 35 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001965742630466857, "min": 0.0001965742630466857, "max": 0.00029838354339596195, "count": 35 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027520396826536, "min": 0.0020886848037717336, "max": 0.0040275772574743, "count": 35 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16552474285714286, "min": 0.16552474285714286, "max": 0.19946118095238097, "count": 35 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3173464, "min": 1.3962282666666668, "max": 2.8425257, "count": 35 }, "Pyramids.Policy.Beta.mean": { "value": 0.006555921811428571, "min": 0.006555921811428571, "max": 0.009946171977142856, "count": 35 }, "Pyramids.Policy.Beta.sum": { "value": 0.09178290536, "min": 0.06962320384, "max": 0.13426831743, "count": 35 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00962457899004221, "min": 0.009282040409743786, "max": 0.42194098234176636, "count": 35 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13474410772323608, "min": 0.12994857132434845, "max": 2.9535868167877197, "count": 35 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 371.2530120481928, "min": 273.0450450450451, "max": 999.0, "count": 35 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30814.0, "min": 15984.0, "max": 32986.0, "count": 35 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5096190247152532, "min": -1.0000000521540642, "max": 1.7283214155052389, "count": 35 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 126.80799807608128, "min": -31.998401671648026, "max": 193.57199853658676, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5096190247152532, "min": -1.0000000521540642, "max": 1.7283214155052389, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 126.80799807608128, "min": -31.998401671648026, "max": 193.57199853658676, "count": 35 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03657803679414515, "min": 0.026313126637303088, "max": 9.021233222447336, "count": 35 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0725550907081924, "min": 2.7085161760624032, "max": 144.33973155915737, "count": 35 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1695909026", "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": "1695911531" }, "total": 2504.8969781309997, "count": 1, "self": 0.529023039999629, "children": { "run_training.setup": { "total": 0.07166386300013983, "count": 1, "self": 0.07166386300013983 }, "TrainerController.start_learning": { "total": 2504.296291228, "count": 1, "self": 1.4716101600106413, "children": { "TrainerController._reset_env": { "total": 5.443028018999939, "count": 1, "self": 5.443028018999939 }, "TrainerController.advance": { "total": 2497.380538057989, "count": 68637, "self": 1.5497346001657206, "children": { "env_step": { "total": 1741.5879476968955, "count": 68637, "self": 1615.993453858799, "children": { "SubprocessEnvManager._take_step": { "total": 124.70773154302697, "count": 68637, "self": 5.120139668008733, "children": { "TorchPolicy.evaluate": { "total": 119.58759187501823, "count": 67028, "self": 119.58759187501823 } } }, "workers": { "total": 0.8867622950695022, "count": 68636, "self": 0.0, "children": { "worker_root": { "total": 2498.6923350129755, "count": 68636, "is_parallel": true, "self": 1008.5282704829297, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025243420000151673, "count": 1, "is_parallel": true, "self": 0.0006848880000234203, "children": { "_process_rank_one_or_two_observation": { "total": 0.001839453999991747, "count": 8, "is_parallel": true, "self": 0.001839453999991747 } } }, "UnityEnvironment.step": { "total": 0.05495165199999974, "count": 1, "is_parallel": true, "self": 0.0005391039999267377, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006434140000237676, "count": 1, "is_parallel": true, "self": 0.0006434140000237676 }, "communicator.exchange": { "total": 0.05105042300010609, "count": 1, "is_parallel": true, "self": 0.05105042300010609 }, "steps_from_proto": { "total": 0.0027187109999431414, "count": 1, "is_parallel": true, "self": 0.00040760299975772796, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023111080001854134, "count": 8, "is_parallel": true, "self": 0.0023111080001854134 } } } } } } }, "UnityEnvironment.step": { "total": 1490.1640645300458, "count": 68635, "is_parallel": true, "self": 36.34467278203124, "children": { "UnityEnvironment._generate_step_input": { "total": 26.933124654964104, "count": 68635, "is_parallel": true, "self": 26.933124654964104 }, "communicator.exchange": { "total": 1311.40155717103, "count": 68635, "is_parallel": true, "self": 1311.40155717103 }, "steps_from_proto": { "total": 115.48470992202056, "count": 68635, "is_parallel": true, "self": 22.853149311328025, "children": { "_process_rank_one_or_two_observation": { "total": 92.63156061069253, "count": 549080, "is_parallel": true, "self": 92.63156061069253 } } } } } } } } } } }, "trainer_advance": { "total": 754.2428557609273, "count": 68636, "self": 2.779412121964924, "children": { "process_trajectory": { "total": 124.65618517096323, "count": 68636, "self": 124.4426094359635, "children": { "RLTrainer._checkpoint": { "total": 0.21357573499972204, "count": 2, "self": 0.21357573499972204 } } }, "_update_policy": { "total": 626.8072584679992, "count": 485, "self": 401.8664659830117, "children": { "TorchPPOOptimizer.update": { "total": 224.94079248498747, "count": 24423, "self": 224.94079248498747 } } } } } } }, "trainer_threads": { "total": 1.2830005289288238e-06, "count": 1, "self": 1.2830005289288238e-06 }, "TrainerController._save_models": { "total": 0.0011137080000480637, "count": 1, "self": 2.6988999707100447e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0010867190003409632, "count": 1, "self": 0.0010867190003409632 } } } } } } }