{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3164612948894501, "min": 0.3079012632369995, "max": 1.433062195777893, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9539.4091796875, "min": 9296.1552734375, "max": 43473.375, "count": 33 }, "Pyramids.Step.mean": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989961.0, "min": 29952.0, "max": 989961.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6362255811691284, "min": -0.08559349179267883, "max": 0.6650585532188416, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.77938842773438, "min": -20.62803077697754, "max": 190.87181091308594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009952552616596222, "min": -0.01849052682518959, "max": 0.4459307789802551, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.7966673374176025, "min": -4.863008499145508, "max": 105.68559265136719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06864753445205722, "min": 0.06397803956044773, "max": 0.07250913445063652, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9610654823288011, "min": 0.4794036922222017, "max": 1.0665216220077127, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01607535640955792, "min": 0.0005407533054114443, "max": 0.01885776720952154, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22505498973381088, "min": 0.004326026443291555, "max": 0.26400874093330157, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.515290352078572e-06, "min": 7.515290352078572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001052140649291, "min": 0.0001052140649291, "max": 0.0033826835724388993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250506428571429, "min": 0.10250506428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350709000000001, "min": 1.3691136000000002, "max": 2.5277620000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026025592214285717, "min": 0.00026025592214285717, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036435829100000005, "min": 0.0036435829100000005, "max": 0.11278335389000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013431372120976448, "min": 0.013431372120976448, "max": 0.6062003970146179, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18803921341896057, "min": 0.18803921341896057, "max": 4.24340295791626, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 308.9130434782609, "min": 272.64285714285717, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28420.0, "min": 15984.0, "max": 32798.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.625856508055459, "min": -1.0000000521540642, "max": 1.7044719904661179, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 149.57879874110222, "min": -32.000001668930054, "max": 187.46199847012758, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.625856508055459, "min": -1.0000000521540642, "max": 1.7044719904661179, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 149.57879874110222, "min": -32.000001668930054, "max": 187.46199847012758, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04282578554367596, "min": 0.038690549169197244, "max": 12.699021624401212, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9399722700181883, "min": 3.9399722700181883, "max": 203.1843459904194, "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": "1719500438", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/PyramidsRND.yaml --env=/content/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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719503723" }, "total": 3285.544901331, "count": 1, "self": 0.6961744560003353, "children": { "run_training.setup": { "total": 0.07229135299985501, "count": 1, "self": 0.07229135299985501 }, "TrainerController.start_learning": { "total": 3284.7764355219997, "count": 1, "self": 2.231652660009786, "children": { "TrainerController._reset_env": { "total": 2.9313808130000325, "count": 1, "self": 2.9313808130000325 }, "TrainerController.advance": { "total": 3279.5276752599884, "count": 64140, "self": 2.516240050958004, "children": { "env_step": { "total": 2237.4579338289977, "count": 64140, "self": 2079.640005545929, "children": { "SubprocessEnvManager._take_step": { "total": 156.39211676001082, "count": 64140, "self": 6.561820003000548, "children": { "TorchPolicy.evaluate": { "total": 149.83029675701027, "count": 62560, "self": 149.83029675701027 } } }, "workers": { "total": 1.4258115230582007, "count": 64140, "self": 0.0, "children": { "worker_root": { "total": 3277.3102046259905, "count": 64140, "is_parallel": true, "self": 1379.88545055205, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004558414000030098, "count": 1, "is_parallel": true, "self": 0.001313592000542485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032448219994876126, "count": 8, "is_parallel": true, "self": 0.0032448219994876126 } } }, "UnityEnvironment.step": { "total": 0.06632136899997931, "count": 1, "is_parallel": true, "self": 0.0008938649998526671, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005408270001225901, "count": 1, "is_parallel": true, "self": 0.0005408270001225901 }, "communicator.exchange": { "total": 0.06257284000002983, "count": 1, "is_parallel": true, "self": 0.06257284000002983 }, "steps_from_proto": { "total": 0.002313836999974228, "count": 1, "is_parallel": true, "self": 0.00041863600017677527, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018952009997974528, "count": 8, "is_parallel": true, "self": 0.0018952009997974528 } } } } } } }, "UnityEnvironment.step": { "total": 1897.4247540739404, "count": 64139, "is_parallel": true, "self": 49.986979416052236, "children": { "UnityEnvironment._generate_step_input": { "total": 30.90677041496565, "count": 64139, "is_parallel": true, "self": 30.90677041496565 }, "communicator.exchange": { "total": 1684.841212373907, "count": 64139, "is_parallel": true, "self": 1684.841212373907 }, "steps_from_proto": { "total": 131.6897918690156, "count": 64139, "is_parallel": true, "self": 28.37178584190383, "children": { "_process_rank_one_or_two_observation": { "total": 103.31800602711178, "count": 513112, "is_parallel": true, "self": 103.31800602711178 } } } } } } } } } } }, "trainer_advance": { "total": 1039.5535013800327, "count": 64140, "self": 4.251810807149695, "children": { "process_trajectory": { "total": 161.68420717888398, "count": 64140, "self": 161.49820693888455, "children": { "RLTrainer._checkpoint": { "total": 0.18600023999943005, "count": 2, "self": 0.18600023999943005 } } }, "_update_policy": { "total": 873.617483393999, "count": 445, "self": 363.5463774349439, "children": { "TorchPPOOptimizer.update": { "total": 510.0711059590551, "count": 22848, "self": 510.0711059590551 } } } } } } }, "trainer_threads": { "total": 9.620007404009812e-07, "count": 1, "self": 9.620007404009812e-07 }, "TrainerController._save_models": { "total": 0.08572582700071507, "count": 1, "self": 0.002646373000970925, "children": { "RLTrainer._checkpoint": { "total": 0.08307945399974415, "count": 1, "self": 0.08307945399974415 } } } } } } }