{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3340718746185303, "min": 0.33222684264183044, "max": 1.5034092664718628, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9995.4306640625, "min": 9995.4306640625, "max": 45607.421875, "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": 0.5394849181175232, "min": -0.10450363159179688, "max": 0.5983114838600159, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.43731689453125, "min": -25.08087158203125, "max": 168.12551879882812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.01266008336097002, "min": -0.04370701313018799, "max": 0.23411716520786285, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.506843090057373, "min": -11.97572135925293, "max": 55.711578369140625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07201122210050624, "min": 0.06485721721574442, "max": 0.07292315159994112, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0801683315075936, "min": 0.46249806178896286, "max": 1.0801683315075936, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017981822822346456, "min": 0.0004128206098600024, "max": 0.017981822822346456, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.26972734233519685, "min": 0.003302564878880019, "max": 0.26972734233519685, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.545017485026668e-06, "min": 7.545017485026668e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011317526227540002, "min": 0.00011317526227540002, "max": 0.0033828968723677998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251497333333334, "min": 0.10251497333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377246000000002, "min": 1.3691136000000002, "max": 2.5276322, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002612458360000001, "min": 0.0002612458360000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003918687540000001, "min": 0.003918687540000001, "max": 0.11279045678, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008015100844204426, "min": 0.008015100844204426, "max": 0.2977636158466339, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12022651731967926, "min": 0.11672012507915497, "max": 2.0843453407287598, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 339.81720430107526, "min": 302.6734693877551, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31603.0, "min": 15984.0, "max": 32678.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5741376211085627, "min": -1.0000000521540642, "max": 1.634163250196345, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 146.39479876309633, "min": -32.000001668930054, "max": 160.1479985192418, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5741376211085627, "min": -1.0000000521540642, "max": 1.634163250196345, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 146.39479876309633, "min": -32.000001668930054, "max": 160.1479985192418, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02817496356444173, "min": 0.02697721658617898, "max": 6.430233513005078, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.620271611493081, "min": 2.5888713077874854, "max": 102.88373620808125, "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": "1752760630", "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": "1752762750" }, "total": 2120.052091364, "count": 1, "self": 0.49347980599941366, "children": { "run_training.setup": { "total": 0.022259015000031468, "count": 1, "self": 0.022259015000031468 }, "TrainerController.start_learning": { "total": 2119.5363525430002, "count": 1, "self": 1.1917173010292572, "children": { "TrainerController._reset_env": { "total": 3.488177567999969, "count": 1, "self": 3.488177567999969 }, "TrainerController.advance": { "total": 2114.777716427971, "count": 64036, "self": 1.3152499849438755, "children": { "env_step": { "total": 1470.0159775419784, "count": 64036, "self": 1329.310269767989, "children": { "SubprocessEnvManager._take_step": { "total": 140.00458925497935, "count": 64036, "self": 4.38086357596228, "children": { "TorchPolicy.evaluate": { "total": 135.62372567901707, "count": 62566, "self": 135.62372567901707 } } }, "workers": { "total": 0.7011185190100377, "count": 64036, "self": 0.0, "children": { "worker_root": { "total": 2114.6111516220467, "count": 64036, "is_parallel": true, "self": 890.1651454600619, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005463084999973944, "count": 1, "is_parallel": true, "self": 0.0036598540002614754, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018032309997124685, "count": 8, "is_parallel": true, "self": 0.0018032309997124685 } } }, "UnityEnvironment.step": { "total": 0.04640874200003964, "count": 1, "is_parallel": true, "self": 0.0005401699999083576, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044622000007166207, "count": 1, "is_parallel": true, "self": 0.00044622000007166207 }, "communicator.exchange": { "total": 0.043878334000055474, "count": 1, "is_parallel": true, "self": 0.043878334000055474 }, "steps_from_proto": { "total": 0.0015440180000041437, "count": 1, "is_parallel": true, "self": 0.00033444400014559506, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012095739998585486, "count": 8, "is_parallel": true, "self": 0.0012095739998585486 } } } } } } }, "UnityEnvironment.step": { "total": 1224.4460061619848, "count": 64035, "is_parallel": true, "self": 31.065984980959456, "children": { "UnityEnvironment._generate_step_input": { "total": 21.6132656800238, "count": 64035, "is_parallel": true, "self": 21.6132656800238 }, "communicator.exchange": { "total": 1080.9718131220166, "count": 64035, "is_parallel": true, "self": 1080.9718131220166 }, "steps_from_proto": { "total": 90.79494237898507, "count": 64035, "is_parallel": true, "self": 17.740818652910434, "children": { "_process_rank_one_or_two_observation": { "total": 73.05412372607464, "count": 512280, "is_parallel": true, "self": 73.05412372607464 } } } } } } } } } } }, "trainer_advance": { "total": 643.4464889010486, "count": 64036, "self": 2.333196006049093, "children": { "process_trajectory": { "total": 120.65255062799952, "count": 64036, "self": 120.2499624679997, "children": { "RLTrainer._checkpoint": { "total": 0.4025881599998229, "count": 2, "self": 0.4025881599998229 } } }, "_update_policy": { "total": 520.460742267, "count": 439, "self": 289.3705557910248, "children": { "TorchPPOOptimizer.update": { "total": 231.0901864759752, "count": 22836, "self": 231.0901864759752 } } } } } } }, "trainer_threads": { "total": 8.259999049187172e-07, "count": 1, "self": 8.259999049187172e-07 }, "TrainerController._save_models": { "total": 0.07874042000003101, "count": 1, "self": 0.0010891739998442063, "children": { "RLTrainer._checkpoint": { "total": 0.0776512460001868, "count": 1, "self": 0.0776512460001868 } } } } } } }