{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5119559168815613, "min": 0.5034074187278748, "max": 1.4569073915481567, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15391.443359375, "min": 14965.294921875, "max": 44196.7421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4965977966785431, "min": -0.10757958143949509, "max": 0.5024316310882568, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 135.57119750976562, "min": -25.926679611206055, "max": 138.168701171875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.14437216520309448, "min": -0.05144139751791954, "max": 0.2575911283493042, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 39.41360092163086, "min": -14.043501853942871, "max": 62.33705520629883, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06429459458592114, "min": 0.06290810950304399, "max": 0.0730116966252262, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.900124324202896, "min": 0.49941473010805, "max": 1.0316345880079705, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01575176536780342, "min": 0.0006719232966448452, "max": 0.016589767467285996, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2205247151492479, "min": 0.0073911562630932974, "max": 0.23225674454200393, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.292690426278571e-06, "min": 7.292690426278571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010209766596789999, "min": 0.00010209766596789999, "max": 0.0032539844153385996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243086428571431, "min": 0.10243086428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340321000000003, "min": 1.3886848, "max": 2.4016496, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025284334214285717, "min": 0.00025284334214285717, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035398067900000007, "min": 0.0035398067900000007, "max": 0.10848767386000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006991219241172075, "min": 0.006991219241172075, "max": 0.430558443069458, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09787707030773163, "min": 0.09787707030773163, "max": 3.013909101486206, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 394.2987012987013, "min": 344.4318181818182, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30361.0, "min": 15984.0, "max": 32663.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4757895884769303, "min": -1.0000000521540642, "max": 1.6100999810309573, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 113.63579831272364, "min": -30.359001725912094, "max": 141.68879833072424, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4757895884769303, "min": -1.0000000521540642, "max": 1.6100999810309573, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 113.63579831272364, "min": -30.359001725912094, "max": 141.68879833072424, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028597743684908243, "min": 0.02780689784611406, "max": 9.7458865782246, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2020262637379346, "min": 2.2020262637379346, "max": 155.9341852515936, "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": "1761130414", "python_version": "3.10.18 (main, Sep 2 2025, 14:19:37) [Clang 20.1.4 ]", "command_line_arguments": "/home/kali/HFRLCourse/unit5/.venv/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --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+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1761131659" }, "total": 1244.615810724, "count": 1, "self": 0.2694132350000018, "children": { "run_training.setup": { "total": 0.013962421999963226, "count": 1, "self": 0.013962421999963226 }, "TrainerController.start_learning": { "total": 1244.332435067, "count": 1, "self": 0.8393597730209876, "children": { "TrainerController._reset_env": { "total": 4.279692654000087, "count": 1, "self": 4.279692654000087 }, "TrainerController.advance": { "total": 1239.177523711979, "count": 63612, "self": 0.6828005569375364, "children": { "env_step": { "total": 947.8981407069955, "count": 63612, "self": 898.6912184359851, "children": { "SubprocessEnvManager._take_step": { "total": 48.66240158897756, "count": 63612, "self": 1.9695368339429251, "children": { "TorchPolicy.evaluate": { "total": 46.692864755034634, "count": 62554, "self": 46.692864755034634 } } }, "workers": { "total": 0.5445206820328394, "count": 63612, "self": 0.0, "children": { "worker_root": { "total": 1242.009381177011, "count": 63612, "is_parallel": true, "self": 396.22949405805855, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001819523999984085, "count": 1, "is_parallel": true, "self": 0.0006689489998734643, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011505750001106207, "count": 8, "is_parallel": true, "self": 0.0011505750001106207 } } }, "UnityEnvironment.step": { "total": 0.028025157000001855, "count": 1, "is_parallel": true, "self": 0.0001569569999446685, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00015895100000307139, "count": 1, "is_parallel": true, "self": 0.00015895100000307139 }, "communicator.exchange": { "total": 0.026012844999968365, "count": 1, "is_parallel": true, "self": 0.026012844999968365 }, "steps_from_proto": { "total": 0.0016964040000857494, "count": 1, "is_parallel": true, "self": 0.00014630800035320135, "children": { "_process_rank_one_or_two_observation": { "total": 0.001550095999732548, "count": 8, "is_parallel": true, "self": 0.001550095999732548 } } } } } } }, "UnityEnvironment.step": { "total": 845.7798871189524, "count": 63611, "is_parallel": true, "self": 9.647923194920963, "children": { "UnityEnvironment._generate_step_input": { "total": 7.677414510994026, "count": 63611, "is_parallel": true, "self": 7.677414510994026 }, "communicator.exchange": { "total": 798.7448140880049, "count": 63611, "is_parallel": true, "self": 798.7448140880049 }, "steps_from_proto": { "total": 29.70973532503251, "count": 63611, "is_parallel": true, "self": 7.056422167005735, "children": { "_process_rank_one_or_two_observation": { "total": 22.653313158026776, "count": 508888, "is_parallel": true, "self": 22.653313158026776 } } } } } } } } } } }, "trainer_advance": { "total": 290.596582448046, "count": 63612, "self": 1.5125231610353467, "children": { "process_trajectory": { "total": 55.1328491810076, "count": 63612, "self": 54.99991200400757, "children": { "RLTrainer._checkpoint": { "total": 0.13293717700003072, "count": 2, "self": 0.13293717700003072 } } }, "_update_policy": { "total": 233.95121010600303, "count": 441, "self": 120.07437019402391, "children": { "TorchPPOOptimizer.update": { "total": 113.87683991197912, "count": 22812, "self": 113.87683991197912 } } } } } } }, "trainer_threads": { "total": 6.610000582440989e-07, "count": 1, "self": 6.610000582440989e-07 }, "TrainerController._save_models": { "total": 0.03585826699986683, "count": 1, "self": 0.0018302670000593935, "children": { "RLTrainer._checkpoint": { "total": 0.034027999999807435, "count": 1, "self": 0.034027999999807435 } } } } } } }