{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.222894549369812, "min": 1.1957294940948486, "max": 2.86820387840271, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11703.1005859375, "min": 11703.1005859375, "max": 29341.7265625, "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": 10.77051067352295, "min": 0.3626998960971832, "max": 10.77051067352295, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2100.24951171875, "min": 70.36377716064453, "max": 2165.253662109375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07178348389838814, "min": 0.062435955798005746, "max": 0.07329488800000855, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28713393559355255, "min": 0.24974382319202298, "max": 0.35899226152504726, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20851520704580287, "min": 0.1271367534908338, "max": 0.2848715939358169, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8340608281832115, "min": 0.5085470139633352, "max": 1.4243579696790845, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.3880973060000045e-06, "min": 5.3880973060000045e-06, "max": 0.00019458800270600002, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.1552389224000018e-05, "min": 2.1552389224000018e-05, "max": 0.0009234400382800001, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 21.477272727272727, "min": 3.9545454545454546, "max": 21.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 945.0, "min": 174.0, "max": 1181.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 21.477272727272727, "min": 3.9545454545454546, "max": 21.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 945.0, "min": 174.0, "max": 1181.0, "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": "1704866611", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "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": "1704867101" }, "total": 489.77684522200025, "count": 1, "self": 0.4433606500001588, "children": { "run_training.setup": { "total": 0.07348486699993373, "count": 1, "self": 0.07348486699993373 }, "TrainerController.start_learning": { "total": 489.25999970500015, "count": 1, "self": 0.635392456973932, "children": { "TrainerController._reset_env": { "total": 3.245709869999928, "count": 1, "self": 3.245709869999928 }, "TrainerController.advance": { "total": 485.2848102610267, "count": 18201, "self": 0.3073347400111288, "children": { "env_step": { "total": 484.97747552101555, "count": 18201, "self": 321.36732814397965, "children": { "SubprocessEnvManager._take_step": { "total": 163.30507186102068, "count": 18201, "self": 1.5870296060190867, "children": { "TorchPolicy.evaluate": { "total": 161.7180422550016, "count": 18201, "self": 161.7180422550016 } } }, "workers": { "total": 0.3050755160152221, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 487.80972605001284, "count": 18201, "is_parallel": true, "self": 240.0891703279667, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005092842999829372, "count": 1, "is_parallel": true, "self": 0.0037259790001371584, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013668639996922138, "count": 10, "is_parallel": true, "self": 0.0013668639996922138 } } }, "UnityEnvironment.step": { "total": 0.04166752800006179, "count": 1, "is_parallel": true, "self": 0.0008131489998959296, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004406440000366274, "count": 1, "is_parallel": true, "self": 0.0004406440000366274 }, "communicator.exchange": { "total": 0.03804670099998475, "count": 1, "is_parallel": true, "self": 0.03804670099998475 }, "steps_from_proto": { "total": 0.0023670340001444856, "count": 1, "is_parallel": true, "self": 0.0006308840002020588, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017361499999424268, "count": 10, "is_parallel": true, "self": 0.0017361499999424268 } } } } } } }, "UnityEnvironment.step": { "total": 247.72055572204613, "count": 18200, "is_parallel": true, "self": 11.638204057072471, "children": { "UnityEnvironment._generate_step_input": { "total": 5.908854284994277, "count": 18200, "is_parallel": true, "self": 5.908854284994277 }, "communicator.exchange": { "total": 192.1602811730029, "count": 18200, "is_parallel": true, "self": 192.1602811730029 }, "steps_from_proto": { "total": 38.013216206976495, "count": 18200, "is_parallel": true, "self": 7.181475276964193, "children": { "_process_rank_one_or_two_observation": { "total": 30.8317409300123, "count": 182000, "is_parallel": true, "self": 30.8317409300123 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018326700001125573, "count": 1, "self": 0.00018326700001125573, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 478.93540711298965, "count": 719943, "is_parallel": true, "self": 15.77938000191898, "children": { "process_trajectory": { "total": 266.8500336260706, "count": 719943, "is_parallel": true, "self": 265.96158975507046, "children": { "RLTrainer._checkpoint": { "total": 0.8884438710001632, "count": 4, "is_parallel": true, "self": 0.8884438710001632 } } }, "_update_policy": { "total": 196.30599348500004, "count": 90, "is_parallel": true, "self": 63.336505664001834, "children": { "TorchPPOOptimizer.update": { "total": 132.9694878209982, "count": 4584, "is_parallel": true, "self": 132.9694878209982 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09390384999960588, "count": 1, "self": 0.0010446769997543015, "children": { "RLTrainer._checkpoint": { "total": 0.09285917299985158, "count": 1, "self": 0.09285917299985158 } } } } } } }