{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7586241960525513, "min": 0.7586241960525513, "max": 2.8544113636016846, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7276.72314453125, "min": 7276.72314453125, "max": 29552.62109375, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.935254096984863, "min": 0.49685052037239075, "max": 12.935254096984863, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1306.460693359375, "min": 48.19449996948242, "max": 1306.460693359375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.692307692307693, "min": 4.545454545454546, "max": 25.692307692307693, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1336.0, "min": 200.0, "max": 1368.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.692307692307693, "min": 4.545454545454546, "max": 25.692307692307693, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1336.0, "min": 200.0, "max": 1368.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06971587601374246, "min": 0.06252595739651416, "max": 0.07932468573163336, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27886350405496985, "min": 0.2512164670034134, "max": 0.38023306122825795, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21430498339674053, "min": 0.15694370387377693, "max": 0.28470112056124447, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8572199335869621, "min": 0.6277748154951077, "max": 1.4235056028062223, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.950097350000008e-06, "min": 7.950097350000008e-06, "max": 0.00029175000274999995, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.180038940000003e-05, "min": 3.180038940000003e-05, "max": 0.0013845000385, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10265, "min": 0.10265, "max": 0.19725000000000004, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4106, "min": 0.4106, "max": 0.9615, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014223500000000013, "min": 0.00014223500000000013, "max": 0.004862775, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005689400000000005, "min": 0.0005689400000000005, "max": 0.023078849999999998, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1753713753", "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=SnowballTarget10 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1753714150" }, "total": 396.793191234, "count": 1, "self": 0.4292780040002526, "children": { "run_training.setup": { "total": 0.03202699799999209, "count": 1, "self": 0.03202699799999209 }, "TrainerController.start_learning": { "total": 396.33188623199976, "count": 1, "self": 0.3077648999885696, "children": { "TrainerController._reset_env": { "total": 2.154582571999981, "count": 1, "self": 2.154582571999981 }, "TrainerController.advance": { "total": 393.79389522701126, "count": 18200, "self": 0.35139653600026577, "children": { "env_step": { "total": 282.4045093190284, "count": 18200, "self": 218.07722089307072, "children": { "SubprocessEnvManager._take_step": { "total": 64.13332768598366, "count": 18200, "self": 1.1586363560104473, "children": { "TorchPolicy.evaluate": { "total": 62.97469132997321, "count": 18200, "self": 62.97469132997321 } } }, "workers": { "total": 0.19396073997404528, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 395.0735726729845, "count": 18200, "is_parallel": true, "self": 202.94649992893642, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018547719998878165, "count": 1, "is_parallel": true, "self": 0.0005407570001807471, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013140149997070694, "count": 10, "is_parallel": true, "self": 0.0013140149997070694 } } }, "UnityEnvironment.step": { "total": 0.03833118700003979, "count": 1, "is_parallel": true, "self": 0.0007042439999622729, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003785149999657733, "count": 1, "is_parallel": true, "self": 0.0003785149999657733 }, "communicator.exchange": { "total": 0.034344431000135955, "count": 1, "is_parallel": true, "self": 0.034344431000135955 }, "steps_from_proto": { "total": 0.0029039969999757886, "count": 1, "is_parallel": true, "self": 0.00045152600000619714, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024524709999695915, "count": 10, "is_parallel": true, "self": 0.0024524709999695915 } } } } } } }, "UnityEnvironment.step": { "total": 192.12707274404806, "count": 18199, "is_parallel": true, "self": 9.377790536154862, "children": { "UnityEnvironment._generate_step_input": { "total": 5.07854646598571, "count": 18199, "is_parallel": true, "self": 5.07854646598571 }, "communicator.exchange": { "total": 148.15007760494404, "count": 18199, "is_parallel": true, "self": 148.15007760494404 }, "steps_from_proto": { "total": 29.520658136963448, "count": 18199, "is_parallel": true, "self": 5.2074960119648495, "children": { "_process_rank_one_or_two_observation": { "total": 24.3131621249986, "count": 181990, "is_parallel": true, "self": 24.3131621249986 } } } } } } } } } } }, "trainer_advance": { "total": 111.03798937198258, "count": 18200, "self": 0.3815790689959613, "children": { "process_trajectory": { "total": 20.794334337989085, "count": 18200, "self": 20.38428447798924, "children": { "RLTrainer._checkpoint": { "total": 0.41004985999984456, "count": 4, "self": 0.41004985999984456 } } }, "_update_policy": { "total": 89.86207596499753, "count": 90, "self": 37.33359989100086, "children": { "TorchPPOOptimizer.update": { "total": 52.52847607399667, "count": 4590, "self": 52.52847607399667 } } } } } } }, "trainer_threads": { "total": 9.139998837781604e-07, "count": 1, "self": 9.139998837781604e-07 }, "TrainerController._save_models": { "total": 0.07564261900006386, "count": 1, "self": 0.0007836929999029962, "children": { "RLTrainer._checkpoint": { "total": 0.07485892600016086, "count": 1, "self": 0.07485892600016086 } } } } } } }