{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5054389834403992, "min": 0.5054389834403992, "max": 1.4887460470199585, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15195.517578125, "min": 15195.517578125, "max": 45162.6015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989872.0, "min": 29929.0, "max": 989872.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989872.0, "min": 29929.0, "max": 989872.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4794197678565979, "min": -0.0907188355922699, "max": 0.5055550932884216, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.92276000976562, "min": -22.044677734375, "max": 142.5665283203125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012201234698295593, "min": -0.016036972403526306, "max": 0.39961737394332886, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.3065345287323, "min": -4.522426128387451, "max": 94.70932006835938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06930266874542339, "min": 0.06397790551894535, "max": 0.07379962227978033, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9702373624359275, "min": 0.47672827167291965, "max": 1.0549287049062137, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016435038556389808, "min": 0.0011488044866088264, "max": 0.018728145837182332, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23009053978945732, "min": 0.011488044866088263, "max": 0.26219404172055266, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.207147597649999e-06, "min": 7.207147597649999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001009000663671, "min": 0.0001009000663671, "max": 0.003504933531688899, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10240235, "min": 0.10240235, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4336329, "min": 1.3886848, "max": 2.5683111, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00024999476500000005, "min": 0.00024999476500000005, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0034999267100000006, "min": 0.0034999267100000006, "max": 0.11685427889, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009728473611176014, "min": 0.008786574006080627, "max": 0.41023382544517517, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13619862496852875, "min": 0.12301203608512878, "max": 2.8716368675231934, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 389.2763157894737, "min": 355.6235294117647, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29585.0, "min": 16856.0, "max": 32922.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5366986804194265, "min": -1.0000000521540642, "max": 1.6131835092516507, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 118.32579839229584, "min": -31.00000161677599, "max": 137.1205982863903, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5366986804194265, "min": -1.0000000521540642, "max": 1.6131835092516507, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 118.32579839229584, "min": -31.00000161677599, "max": 137.1205982863903, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.039290871180128306, "min": 0.03595578232125263, "max": 7.917780039065025, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0253970808698796, "min": 2.792343703637016, "max": 134.60226066410542, "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": "1703424379", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703426546" }, "total": 2167.447547816, "count": 1, "self": 0.4756289619999734, "children": { "run_training.setup": { "total": 0.06844011700002284, "count": 1, "self": 0.06844011700002284 }, "TrainerController.start_learning": { "total": 2166.903478737, "count": 1, "self": 1.2243080470434506, "children": { "TrainerController._reset_env": { "total": 2.4276302289999876, "count": 1, "self": 2.4276302289999876 }, "TrainerController.advance": { "total": 2163.1704864899566, "count": 63746, "self": 1.3060747380004614, "children": { "env_step": { "total": 1529.225074084939, "count": 63746, "self": 1406.4002907918712, "children": { "SubprocessEnvManager._take_step": { "total": 122.06248050399586, "count": 63746, "self": 4.57470943201929, "children": { "TorchPolicy.evaluate": { "total": 117.48777107197657, "count": 62573, "self": 117.48777107197657 } } }, "workers": { "total": 0.7623027890720095, "count": 63746, "self": 0.0, "children": { "worker_root": { "total": 2162.1696823290335, "count": 63746, "is_parallel": true, "self": 870.9166657920396, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017348989999845799, "count": 1, "is_parallel": true, "self": 0.0005409890002283646, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011939099997562153, "count": 8, "is_parallel": true, "self": 0.0011939099997562153 } } }, "UnityEnvironment.step": { "total": 0.05043402900003002, "count": 1, "is_parallel": true, "self": 0.0006527610001967332, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004954369999268238, "count": 1, "is_parallel": true, "self": 0.0004954369999268238 }, "communicator.exchange": { "total": 0.047692593999954624, "count": 1, "is_parallel": true, "self": 0.047692593999954624 }, "steps_from_proto": { "total": 0.0015932369999518414, "count": 1, "is_parallel": true, "self": 0.00033554999993157253, "children": { "_process_rank_one_or_two_observation": { "total": 0.001257687000020269, "count": 8, "is_parallel": true, "self": 0.001257687000020269 } } } } } } }, "UnityEnvironment.step": { "total": 1291.253016536994, "count": 63745, "is_parallel": true, "self": 34.2750190349409, "children": { "UnityEnvironment._generate_step_input": { "total": 23.4900794400246, "count": 63745, "is_parallel": true, "self": 23.4900794400246 }, "communicator.exchange": { "total": 1137.5250352120156, "count": 63745, "is_parallel": true, "self": 1137.5250352120156 }, "steps_from_proto": { "total": 95.96288285001287, "count": 63745, "is_parallel": true, "self": 18.650780166125855, "children": { "_process_rank_one_or_two_observation": { "total": 77.31210268388702, "count": 509960, "is_parallel": true, "self": 77.31210268388702 } } } } } } } } } } }, "trainer_advance": { "total": 632.6393376670172, "count": 63746, "self": 2.453787488015678, "children": { "process_trajectory": { "total": 125.64570959400226, "count": 63746, "self": 125.46035070100243, "children": { "RLTrainer._checkpoint": { "total": 0.18535889299982955, "count": 2, "self": 0.18535889299982955 } } }, "_update_policy": { "total": 504.5398405849993, "count": 455, "self": 300.74700132896544, "children": { "TorchPPOOptimizer.update": { "total": 203.79283925603386, "count": 22797, "self": 203.79283925603386 } } } } } } }, "trainer_threads": { "total": 1.0390003808424808e-06, "count": 1, "self": 1.0390003808424808e-06 }, "TrainerController._save_models": { "total": 0.0810529319996931, "count": 1, "self": 0.0016387309997298871, "children": { "RLTrainer._checkpoint": { "total": 0.07941420099996321, "count": 1, "self": 0.07941420099996321 } } } } } } }