{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39117008447647095, "min": 0.39117008447647095, "max": 1.3874926567077637, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11716.326171875, "min": 11716.326171875, "max": 42090.9765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4885183572769165, "min": -0.10259263962507248, "max": 0.49886295199394226, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 134.34254455566406, "min": -24.622234344482422, "max": 135.6907196044922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.39171457290649414, "min": -0.39171457290649414, "max": 0.3775857985019684, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -107.72150421142578, "min": -107.72150421142578, "max": 89.48783111572266, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06420213139721283, "min": 0.06420213139721283, "max": 0.07741204125020838, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8988298395609796, "min": 0.5418842887514587, "max": 1.0636121039375819, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.041666058654386905, "min": 0.00019572309647555213, "max": 0.041666058654386905, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.5833248211614167, "min": 0.0025444002541821775, "max": 0.5833248211614167, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.717361713292855e-06, "min": 7.717361713292855e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010804306398609998, "min": 0.00010804306398609998, "max": 0.0035071820309394005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257242142857141, "min": 0.10257242142857141, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360138999999998, "min": 1.3886848, "max": 2.5690605999999994, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026698490071428577, "min": 0.00026698490071428577, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037377886100000007, "min": 0.0037377886100000007, "max": 0.11692915394000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011517086997628212, "min": 0.011517086997628212, "max": 0.4601578712463379, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16123922169208527, "min": 0.16123922169208527, "max": 3.2211050987243652, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 375.1111111111111, "min": 375.1111111111111, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30384.0, "min": 15984.0, "max": 32505.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.496482478454709, "min": -1.0000000521540642, "max": 1.520210496787178, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 119.71859827637672, "min": -29.99740157276392, "max": 120.69399827718735, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.496482478454709, "min": -1.0000000521540642, "max": 1.520210496787178, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 119.71859827637672, "min": -29.99740157276392, "max": 120.69399827718735, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04465150371506752, "min": 0.04465150371506752, "max": 9.906687992624938, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5721202972054016, "min": 3.4984145540802274, "max": 158.50700788199902, "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": "1753102814", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1753104890" }, "total": 2075.7856676419997, "count": 1, "self": 0.4802207089996955, "children": { "run_training.setup": { "total": 0.019076896000115084, "count": 1, "self": 0.019076896000115084 }, "TrainerController.start_learning": { "total": 2075.286370037, "count": 1, "self": 1.1533723400207236, "children": { "TrainerController._reset_env": { "total": 2.0881537280001794, "count": 1, "self": 2.0881537280001794 }, "TrainerController.advance": { "total": 2071.96754530798, "count": 63587, "self": 1.2573153989546881, "children": { "env_step": { "total": 1443.4502421099455, "count": 63587, "self": 1304.718410937899, "children": { "SubprocessEnvManager._take_step": { "total": 138.017714645051, "count": 63587, "self": 4.271144366085537, "children": { "TorchPolicy.evaluate": { "total": 133.74657027896546, "count": 62558, "self": 133.74657027896546 } } }, "workers": { "total": 0.7141165269954399, "count": 63587, "self": 0.0, "children": { "worker_root": { "total": 2071.226892137977, "count": 63587, "is_parallel": true, "self": 870.1991920919268, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017552849999447062, "count": 1, "is_parallel": true, "self": 0.0005989319988657371, "children": { "_process_rank_one_or_two_observation": { "total": 0.001156353001078969, "count": 8, "is_parallel": true, "self": 0.001156353001078969 } } }, "UnityEnvironment.step": { "total": 0.055467268000029435, "count": 1, "is_parallel": true, "self": 0.0005262520003270765, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00049549899995327, "count": 1, "is_parallel": true, "self": 0.00049549899995327 }, "communicator.exchange": { "total": 0.05287118599972018, "count": 1, "is_parallel": true, "self": 0.05287118599972018 }, "steps_from_proto": { "total": 0.0015743310000289057, "count": 1, "is_parallel": true, "self": 0.00032628500048303977, "children": { "_process_rank_one_or_two_observation": { "total": 0.001248045999545866, "count": 8, "is_parallel": true, "self": 0.001248045999545866 } } } } } } }, "UnityEnvironment.step": { "total": 1201.02770004605, "count": 63586, "is_parallel": true, "self": 30.950952952125135, "children": { "UnityEnvironment._generate_step_input": { "total": 22.39365414198255, "count": 63586, "is_parallel": true, "self": 22.39365414198255 }, "communicator.exchange": { "total": 1054.1885846599807, "count": 63586, "is_parallel": true, "self": 1054.1885846599807 }, "steps_from_proto": { "total": 93.49450829196167, "count": 63586, "is_parallel": true, "self": 18.52950341211408, "children": { "_process_rank_one_or_two_observation": { "total": 74.96500487984758, "count": 508688, "is_parallel": true, "self": 74.96500487984758 } } } } } } } } } } }, "trainer_advance": { "total": 627.2599877990797, "count": 63587, "self": 2.31035045709541, "children": { "process_trajectory": { "total": 120.08414666798126, "count": 63587, "self": 119.89432673298188, "children": { "RLTrainer._checkpoint": { "total": 0.18981993499937744, "count": 2, "self": 0.18981993499937744 } } }, "_update_policy": { "total": 504.865490674003, "count": 453, "self": 283.33289647608444, "children": { "TorchPPOOptimizer.update": { "total": 221.53259419791857, "count": 22758, "self": 221.53259419791857 } } } } } } }, "trainer_threads": { "total": 1.0429994290461764e-06, "count": 1, "self": 1.0429994290461764e-06 }, "TrainerController._save_models": { "total": 0.07729761799964763, "count": 1, "self": 0.0012657910001507844, "children": { "RLTrainer._checkpoint": { "total": 0.07603182699949684, "count": 1, "self": 0.07603182699949684 } } } } } } }