{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0309733152389526, "min": 1.0223408937454224, "max": 2.872236967086792, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9889.095703125, "min": 9889.095703125, "max": 29825.30859375, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249968.0, "min": 9952.0, "max": 249968.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249968.0, "min": 9952.0, "max": 249968.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.991127014160156, "min": 0.19872714579105377, "max": 12.991127014160156, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1935.677978515625, "min": 29.411617279052734, "max": 1937.9921875, "count": 25 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 0.4534659683704376, "min": -0.09423504024744034, "max": 0.5309673547744751, "count": 25 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 67.5664291381836, "min": -13.946785926818848, "max": 79.84397888183594, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.272727272727273, "min": 3.5681818181818183, "max": 26.272727272727273, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1156.0, "min": 157.0, "max": 1410.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.272727272727273, "min": 3.5681818181818183, "max": 26.272727272727273, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1156.0, "min": 157.0, "max": 1410.0, "count": 25 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 0.922049364244396, "min": 0.5866856629198248, "max": 1.1919815250418402, "count": 25 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 40.570172026753426, "min": 25.81416916847229, "max": 65.55898387730122, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07002082359908587, "min": 0.06378195678025447, "max": 0.07494797236608529, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.14004164719817175, "min": 0.130625964057496, "max": 0.2171929137094754, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.10313563005012624, "min": 0.06378779209711972, "max": 0.15858229779291388, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.20627126010025248, "min": 0.12757558419423945, "max": 0.4263416723731686, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.1600097680000001e-05, "min": 1.1600097680000001e-05, "max": 0.0004868000026399999, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.3200195360000002e-05, "min": 2.3200195360000002e-05, "max": 0.00128880004224, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10231999999999997, "min": 0.10231999999999997, "max": 0.19736, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20463999999999993, "min": 0.20463999999999993, "max": 0.55776, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.000172168, "min": 0.000172168, "max": 0.006815464, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.000344336, "min": 0.000344336, "max": 0.018047424, "count": 25 }, "SnowballTarget.Losses.CuriosityForwardLoss.mean": { "value": 0.045459338482104095, "min": 0.044405128076380376, "max": 0.10845891888454265, "count": 25 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.09091867696420819, "min": 0.08881025615276075, "max": 0.2169178377690853, "count": 25 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 0.8887747415140563, "min": 0.8759369931968988, "max": 2.7890490363625915, "count": 25 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 1.7775494830281127, "min": 1.7518739863937975, "max": 6.993433725600148, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1756156568", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget_withcuriosity_emp --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": "1756157174" }, "total": 605.3402779439998, "count": 1, "self": 0.7924474359997475, "children": { "run_training.setup": { "total": 0.024062476999915816, "count": 1, "self": 0.024062476999915816 }, "TrainerController.start_learning": { "total": 604.5237680310001, "count": 1, "self": 0.42103206098772716, "children": { "TrainerController._reset_env": { "total": 2.777153333000115, "count": 1, "self": 2.777153333000115 }, "TrainerController.advance": { "total": 601.1980837580127, "count": 22744, "self": 0.4522723569898517, "children": { "env_step": { "total": 365.67106615400644, "count": 22744, "self": 279.60002610396714, "children": { "SubprocessEnvManager._take_step": { "total": 85.81800650901323, "count": 22744, "self": 1.5075768130018332, "children": { "TorchPolicy.evaluate": { "total": 84.3104296960114, "count": 22744, "self": 84.3104296960114 } } }, "workers": { "total": 0.25303354102607045, "count": 22744, "self": 0.0, "children": { "worker_root": { "total": 602.8538616430055, "count": 22744, "is_parallel": true, "self": 357.0347094720273, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005229358000178763, "count": 1, "is_parallel": true, "self": 0.0038612719995398948, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013680860006388684, "count": 10, "is_parallel": true, "self": 0.0013680860006388684 } } }, "UnityEnvironment.step": { "total": 0.03432639199991172, "count": 1, "is_parallel": true, "self": 0.0005874959997527185, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039181800002552336, "count": 1, "is_parallel": true, "self": 0.00039181800002552336 }, "communicator.exchange": { "total": 0.031434717000138335, "count": 1, "is_parallel": true, "self": 0.031434717000138335 }, "steps_from_proto": { "total": 0.001912360999995144, "count": 1, "is_parallel": true, "self": 0.00038692299949616427, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015254380004989798, "count": 10, "is_parallel": true, "self": 0.0015254380004989798 } } } } } } }, "UnityEnvironment.step": { "total": 245.8191521709782, "count": 22743, "is_parallel": true, "self": 12.128484161985853, "children": { "UnityEnvironment._generate_step_input": { "total": 6.543416894011898, "count": 22743, "is_parallel": true, "self": 6.543416894011898 }, "communicator.exchange": { "total": 188.4204561779975, "count": 22743, "is_parallel": true, "self": 188.4204561779975 }, "steps_from_proto": { "total": 38.72679493698297, "count": 22743, "is_parallel": true, "self": 6.844759590040667, "children": { "_process_rank_one_or_two_observation": { "total": 31.882035346942303, "count": 227430, "is_parallel": true, "self": 31.882035346942303 } } } } } } } } } } }, "trainer_advance": { "total": 235.07474524701638, "count": 22744, "self": 0.487355728039347, "children": { "process_trajectory": { "total": 41.2958691859767, "count": 22744, "self": 40.70373681997626, "children": { "RLTrainer._checkpoint": { "total": 0.5921323660004418, "count": 5, "self": 0.5921323660004418 } } }, "_update_policy": { "total": 193.29152033300034, "count": 56, "self": 115.7347897039881, "children": { "TorchPPOOptimizer.update": { "total": 77.55673062901224, "count": 5712, "self": 77.55673062901224 } } } } } } }, "trainer_threads": { "total": 1.1799997992056888e-06, "count": 1, "self": 1.1799997992056888e-06 }, "TrainerController._save_models": { "total": 0.1274976989998322, "count": 1, "self": 0.0007758519996059476, "children": { "RLTrainer._checkpoint": { "total": 0.12672184700022626, "count": 1, "self": 0.12672184700022626 } } } } } } }