{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.735109269618988, "min": 0.6884832978248596, "max": 1.464805245399475, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21782.7578125, "min": 20742.625, "max": 44436.33203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989986.0, "min": 29952.0, "max": 989986.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989986.0, "min": 29952.0, "max": 989986.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.16293205320835114, "min": -0.09712331742048264, "max": 0.16853438317775726, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 41.058876037597656, "min": -23.406719207763672, "max": 42.30213165283203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.15327104926109314, "min": -0.15327104926109314, "max": 0.36652931571006775, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -38.624305725097656, "min": -38.624305725097656, "max": 86.86744689941406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06645582844749424, "min": 0.06565234622324906, "max": 0.07276697853744692, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9303815982649194, "min": 0.50736765695509, "max": 1.017629271838814, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01540837858312637, "min": 5.965881510238594e-05, "max": 0.01540837858312637, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2157173001637692, "min": 0.0008352234114334031, "max": 0.2157173001637692, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.59474746845e-06, "min": 7.59474746845e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001063264645583, "min": 0.0001063264645583, "max": 0.0035081345306219, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253155, "min": 0.10253155, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354417, "min": 1.3886848, "max": 2.5693781, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000262901845, "min": 0.000262901845, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00368062583, "min": 0.00368062583, "max": 0.11696087219, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010531469248235226, "min": 0.010531469248235226, "max": 0.43211010098457336, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.147440567612648, "min": 0.147440567612648, "max": 3.024770736694336, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 690.4418604651163, "min": 690.4418604651163, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29689.0, "min": 15984.0, "max": 32519.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5651953206505886, "min": -1.0000000521540642, "max": 0.5855414267720246, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 24.30339878797531, "min": -31.990401670336723, "max": 24.30339878797531, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5651953206505886, "min": -1.0000000521540642, "max": 0.5855414267720246, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 24.30339878797531, "min": -31.990401670336723, "max": 24.30339878797531, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07651712458586148, "min": 0.07651712458586148, "max": 8.394698396325111, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.290236357192043, "min": 3.290236357192043, "max": 134.31517434120178, "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": "1765872001", "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 /content/ml-agents/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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1765874084" }, "total": 2082.77392529, "count": 1, "self": 0.4315414170000622, "children": { "run_training.setup": { "total": 0.019754939999984344, "count": 1, "self": 0.019754939999984344 }, "TrainerController.start_learning": { "total": 2082.322628933, "count": 1, "self": 1.2413504670680595, "children": { "TrainerController._reset_env": { "total": 2.2720583409995925, "count": 1, "self": 2.2720583409995925 }, "TrainerController.advance": { "total": 2078.7341041839322, "count": 63356, "self": 1.2895543461099805, "children": { "env_step": { "total": 1419.5134830430134, "count": 63356, "self": 1274.9888953350855, "children": { "SubprocessEnvManager._take_step": { "total": 143.787636300945, "count": 63356, "self": 4.3569491440193815, "children": { "TorchPolicy.evaluate": { "total": 139.43068715692561, "count": 62560, "self": 139.43068715692561 } } }, "workers": { "total": 0.7369514069828256, "count": 63356, "self": 0.0, "children": { "worker_root": { "total": 2076.0435217359586, "count": 63356, "is_parallel": true, "self": 911.5100938959881, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016783360001682013, "count": 1, "is_parallel": true, "self": 0.0005458430009639414, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011324929992042598, "count": 8, "is_parallel": true, "self": 0.0011324929992042598 } } }, "UnityEnvironment.step": { "total": 0.04835949800008166, "count": 1, "is_parallel": true, "self": 0.0005300920006447996, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004384719995869091, "count": 1, "is_parallel": true, "self": 0.0004384719995869091 }, "communicator.exchange": { "total": 0.04577221899990036, "count": 1, "is_parallel": true, "self": 0.04577221899990036 }, "steps_from_proto": { "total": 0.0016187149999495887, "count": 1, "is_parallel": true, "self": 0.0003546979996826849, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012640170002669038, "count": 8, "is_parallel": true, "self": 0.0012640170002669038 } } } } } } }, "UnityEnvironment.step": { "total": 1164.5334278399705, "count": 63355, "is_parallel": true, "self": 32.21847700486887, "children": { "UnityEnvironment._generate_step_input": { "total": 23.794540354885157, "count": 63355, "is_parallel": true, "self": 23.794540354885157 }, "communicator.exchange": { "total": 1006.5932505800833, "count": 63355, "is_parallel": true, "self": 1006.5932505800833 }, "steps_from_proto": { "total": 101.92715990013312, "count": 63355, "is_parallel": true, "self": 21.70317819798447, "children": { "_process_rank_one_or_two_observation": { "total": 80.22398170214865, "count": 506840, "is_parallel": true, "self": 80.22398170214865 } } } } } } } } } } }, "trainer_advance": { "total": 657.9310667948089, "count": 63356, "self": 2.4856748936445, "children": { "process_trajectory": { "total": 118.64107234716175, "count": 63356, "self": 118.46503861416204, "children": { "RLTrainer._checkpoint": { "total": 0.1760337329997128, "count": 2, "self": 0.1760337329997128 } } }, "_update_policy": { "total": 536.8043195540026, "count": 452, "self": 296.00705410798173, "children": { "TorchPPOOptimizer.update": { "total": 240.7972654460209, "count": 22794, "self": 240.7972654460209 } } } } } } }, "trainer_threads": { "total": 8.850001904647797e-07, "count": 1, "self": 8.850001904647797e-07 }, "TrainerController._save_models": { "total": 0.07511505599995871, "count": 1, "self": 0.0010758159996839822, "children": { "RLTrainer._checkpoint": { "total": 0.07403924000027473, "count": 1, "self": 0.07403924000027473 } } } } } } }