{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4383413791656494, "min": 0.4383413791656494, "max": 1.4844763278961182, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13052.052734375, "min": 13052.052734375, "max": 45033.07421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989873.0, "min": 29952.0, "max": 989873.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5928688049316406, "min": -0.1241547018289566, "max": 0.5928688049316406, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 166.00326538085938, "min": -29.797128677368164, "max": 166.00326538085938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015947304666042328, "min": 0.002410236280411482, "max": 0.270657479763031, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.465245246887207, "min": 0.6266614198684692, "max": 64.95779418945312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06728138891056881, "min": 0.06580660772225304, "max": 0.07323580199278823, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9419394447479634, "min": 0.49306210547139684, "max": 1.0710496319031033, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016257972797323137, "min": 0.0004731688816048455, "max": 0.018371895974269137, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22761161916252393, "min": 0.003785351052838764, "max": 0.2572065436397679, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.459790370578572e-06, "min": 7.459790370578572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010443706518810001, "min": 0.00010443706518810001, "max": 0.0033827687724105, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024865642857143, "min": 0.1024865642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348119000000001, "min": 1.327104, "max": 2.5275895, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025840777214285724, "min": 0.00025840777214285724, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036177088100000014, "min": 0.0036177088100000014, "max": 0.11278619105, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01466803252696991, "min": 0.013841480948030949, "max": 0.43521907925605774, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20535245537757874, "min": 0.1992916315793991, "max": 3.0465335845947266, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 310.32608695652175, "min": 310.32608695652175, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28550.0, "min": 15984.0, "max": 34045.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6896738931536674, "min": -1.0000000521540642, "max": 1.6896738931536674, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 155.4499981701374, "min": -32.000001668930054, "max": 155.4499981701374, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6896738931536674, "min": -1.0000000521540642, "max": 1.6896738931536674, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 155.4499981701374, "min": -32.000001668930054, "max": 155.4499981701374, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047187314569980474, "min": 0.047187314569980474, "max": 8.782312530092895, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.3412329404382035, "min": 4.231538613006705, "max": 140.51700048148632, "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": "1758770067", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env /content/ml-agents/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": "1758772399" }, "total": 2332.464165835, "count": 1, "self": 0.5412166320002143, "children": { "run_training.setup": { "total": 0.0227612210001098, "count": 1, "self": 0.0227612210001098 }, "TrainerController.start_learning": { "total": 2331.900187982, "count": 1, "self": 1.6903318600116108, "children": { "TrainerController._reset_env": { "total": 2.4887300699997468, "count": 1, "self": 2.4887300699997468 }, "TrainerController.advance": { "total": 2327.643116425988, "count": 63760, "self": 1.6498569399795997, "children": { "env_step": { "total": 1659.407441103997, "count": 63760, "self": 1487.9132741649482, "children": { "SubprocessEnvManager._take_step": { "total": 170.48548738897944, "count": 63760, "self": 5.1629853859499235, "children": { "TorchPolicy.evaluate": { "total": 165.3225020030295, "count": 62557, "self": 165.3225020030295 } } }, "workers": { "total": 1.008679550069246, "count": 63760, "self": 0.0, "children": { "worker_root": { "total": 2325.3451279839883, "count": 63760, "is_parallel": true, "self": 966.9788463619425, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001715664999665023, "count": 1, "is_parallel": true, "self": 0.0005377190000217524, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011779459996432706, "count": 8, "is_parallel": true, "self": 0.0011779459996432706 } } }, "UnityEnvironment.step": { "total": 0.10132787999964421, "count": 1, "is_parallel": true, "self": 0.0013923609990342811, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000505823000366945, "count": 1, "is_parallel": true, "self": 0.000505823000366945 }, "communicator.exchange": { "total": 0.09575473799986867, "count": 1, "is_parallel": true, "self": 0.09575473799986867 }, "steps_from_proto": { "total": 0.0036749580003743176, "count": 1, "is_parallel": true, "self": 0.0023890720003691968, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012858860000051209, "count": 8, "is_parallel": true, "self": 0.0012858860000051209 } } } } } } }, "UnityEnvironment.step": { "total": 1358.3662816220458, "count": 63759, "is_parallel": true, "self": 35.12755044999949, "children": { "UnityEnvironment._generate_step_input": { "total": 24.094914866004274, "count": 63759, "is_parallel": true, "self": 24.094914866004274 }, "communicator.exchange": { "total": 1185.7878828140088, "count": 63759, "is_parallel": true, "self": 1185.7878828140088 }, "steps_from_proto": { "total": 113.35593349203327, "count": 63759, "is_parallel": true, "self": 24.53301057201088, "children": { "_process_rank_one_or_two_observation": { "total": 88.82292292002239, "count": 510072, "is_parallel": true, "self": 88.82292292002239 } } } } } } } } } } }, "trainer_advance": { "total": 666.5858183820114, "count": 63760, "self": 3.0933717080893075, "children": { "process_trajectory": { "total": 127.2687508759268, "count": 63760, "self": 127.02963660292653, "children": { "RLTrainer._checkpoint": { "total": 0.23911427300026844, "count": 2, "self": 0.23911427300026844 } } }, "_update_policy": { "total": 536.2236957979953, "count": 436, "self": 296.7121986079828, "children": { "TorchPPOOptimizer.update": { "total": 239.5114971900125, "count": 22860, "self": 239.5114971900125 } } } } } } }, "trainer_threads": { "total": 9.290006346418522e-07, "count": 1, "self": 9.290006346418522e-07 }, "TrainerController._save_models": { "total": 0.07800869699985924, "count": 1, "self": 0.0010731020001912839, "children": { "RLTrainer._checkpoint": { "total": 0.07693559499966796, "count": 1, "self": 0.07693559499966796 } } } } } } }