{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48063433170318604, "min": 0.4692344069480896, "max": 1.470839023590088, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14388.26953125, "min": 14049.02734375, "max": 44619.37109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989977.0, "min": 29952.0, "max": 989977.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989977.0, "min": 29952.0, "max": 989977.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.44532668590545654, "min": -0.09884803742170334, "max": 0.5579422116279602, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 122.01951599121094, "min": -23.822376251220703, "max": 156.22381591796875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.02150287851691246, "min": -0.02150287851691246, "max": 0.21008716523647308, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.891788482666016, "min": -5.891788482666016, "max": 50.420921325683594, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06535600314895247, "min": 0.06429562698604302, "max": 0.07519610611285459, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9149840440853345, "min": 0.4851201793771697, "max": 1.0769569803575425, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014496754247548304, "min": 0.0004073721338207389, "max": 0.014873691412503831, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20295455946567625, "min": 0.005295837739669606, "max": 0.22310537118755747, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.700668861714284e-06, "min": 7.700668861714284e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010780936406399997, "min": 0.00010780936406399997, "max": 0.003371705276098299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256685714285715, "min": 0.10256685714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.435936, "min": 1.3691136000000002, "max": 2.4424554000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026642902857142864, "min": 0.00026642902857142864, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003730006400000001, "min": 0.003730006400000001, "max": 0.11240777982999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010170450434088707, "min": 0.010170450434088707, "max": 0.3285984396934509, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1423863023519516, "min": 0.1423863023519516, "max": 2.3001890182495117, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 438.69444444444446, "min": 347.86746987951807, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31586.0, "min": 15984.0, "max": 33630.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4223833130672574, "min": -1.0000000521540642, "max": 1.603932511375611, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 102.41159854084253, "min": -32.000001668930054, "max": 133.12639844417572, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4223833130672574, "min": -1.0000000521540642, "max": 1.603932511375611, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 102.41159854084253, "min": -32.000001668930054, "max": 133.12639844417572, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04596105357551197, "min": 0.0393430610749792, "max": 6.373056381009519, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.309195857436862, "min": 3.2654740692232735, "max": 101.9689020961523, "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": "1788610183", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Training --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1788612640" }, "total": 2457.3661236489997, "count": 1, "self": 0.4801017789995967, "children": { "run_training.setup": { "total": 0.019352670999978727, "count": 1, "self": 0.019352670999978727 }, "TrainerController.start_learning": { "total": 2456.866669199, "count": 1, "self": 1.6697714270039796, "children": { "TrainerController._reset_env": { "total": 3.1423468160000994, "count": 1, "self": 3.1423468160000994 }, "TrainerController.advance": { "total": 2451.972584205996, "count": 63645, "self": 1.644876678069977, "children": { "env_step": { "total": 1790.0176028909702, "count": 63645, "self": 1619.0932308129154, "children": { "SubprocessEnvManager._take_step": { "total": 169.93236793501342, "count": 63645, "self": 5.099558166002453, "children": { "TorchPolicy.evaluate": { "total": 164.83280976901096, "count": 62567, "self": 164.83280976901096 } } }, "workers": { "total": 0.992004143041413, "count": 63645, "self": 0.0, "children": { "worker_root": { "total": 2450.9944483749773, "count": 63645, "is_parallel": true, "self": 963.7221945030533, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004482126000084463, "count": 1, "is_parallel": true, "self": 0.0031781590000719007, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013039670000125625, "count": 8, "is_parallel": true, "self": 0.0013039670000125625 } } }, "UnityEnvironment.step": { "total": 0.05009932899997693, "count": 1, "is_parallel": true, "self": 0.0005394040001647227, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004750479999984236, "count": 1, "is_parallel": true, "self": 0.0004750479999984236 }, "communicator.exchange": { "total": 0.0472565359998498, "count": 1, "is_parallel": true, "self": 0.0472565359998498 }, "steps_from_proto": { "total": 0.0018283409999639844, "count": 1, "is_parallel": true, "self": 0.00037147699981687765, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014568640001471067, "count": 8, "is_parallel": true, "self": 0.0014568640001471067 } } } } } } }, "UnityEnvironment.step": { "total": 1487.272253871924, "count": 63644, "is_parallel": true, "self": 36.17591552593467, "children": { "UnityEnvironment._generate_step_input": { "total": 24.96874212199691, "count": 63644, "is_parallel": true, "self": 24.96874212199691 }, "communicator.exchange": { "total": 1307.4988795109437, "count": 63644, "is_parallel": true, "self": 1307.4988795109437 }, "steps_from_proto": { "total": 118.62871671304879, "count": 63644, "is_parallel": true, "self": 25.104068238325908, "children": { "_process_rank_one_or_two_observation": { "total": 93.52464847472288, "count": 509152, "is_parallel": true, "self": 93.52464847472288 } } } } } } } } } } }, "trainer_advance": { "total": 660.3101046369559, "count": 63645, "self": 3.148322349987666, "children": { "process_trajectory": { "total": 118.57478626796637, "count": 63645, "self": 118.32724236396643, "children": { "RLTrainer._checkpoint": { "total": 0.24754390399994008, "count": 2, "self": 0.24754390399994008 } } }, "_update_policy": { "total": 538.5869960190018, "count": 444, "self": 289.10093802799565, "children": { "TorchPPOOptimizer.update": { "total": 249.4860579910062, "count": 22791, "self": 249.4860579910062 } } } } } } }, "trainer_threads": { "total": 8.889996934158262e-07, "count": 1, "self": 8.889996934158262e-07 }, "TrainerController._save_models": { "total": 0.0819658610002989, "count": 1, "self": 0.000925504000406363, "children": { "RLTrainer._checkpoint": { "total": 0.08104035699989254, "count": 1, "self": 0.08104035699989254 } } } } } } }