{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8994150161743164, "min": 0.8685795664787292, "max": 2.8722782135009766, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9131.7607421875, "min": 8274.0888671875, "max": 29415.0, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.722460746765137, "min": 0.26966437697410583, "max": 12.722460746765137, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2480.8798828125, "min": 52.31488800048828, "max": 2604.244140625, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.09898542262289638, "min": 0.0893245171641063, "max": 0.10430966530884866, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3959416904915855, "min": 0.3572980686564252, "max": 0.5215483265442433, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17855720992620083, "min": 0.11213788322593067, "max": 0.2533063365548265, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7142288397048033, "min": 0.4485515329037227, "max": 1.2665316827741324, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.5940987029999965e-06, "min": 2.5940987029999965e-06, "max": 0.000197294001353, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.0376394811999986e-05, "min": 1.0376394811999986e-05, "max": 0.0009617200191400001, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10129700000000001, "min": 0.10129700000000001, "max": 0.19864699999999996, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40518800000000005, "min": 0.40518800000000005, "max": 0.9808600000000002, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.472029999999994e-05, "min": 7.472029999999994e-05, "max": 0.0049324853, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00029888119999999977, "min": 0.00029888119999999977, "max": 0.024044913999999997, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.795454545454547, "min": 3.2954545454545454, "max": 25.12962962962963, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1091.0, "min": 145.0, "max": 1379.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.795454545454547, "min": 3.2954545454545454, "max": 25.12962962962963, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1091.0, "min": 145.0, "max": 1379.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709374777", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709375707" }, "total": 930.3749521529999, "count": 1, "self": 0.8077687090003565, "children": { "run_training.setup": { "total": 0.05089191899969592, "count": 1, "self": 0.05089191899969592 }, "TrainerController.start_learning": { "total": 929.5162915249998, "count": 1, "self": 1.1493701499266535, "children": { "TrainerController._reset_env": { "total": 3.0749490230000447, "count": 1, "self": 3.0749490230000447 }, "TrainerController.advance": { "total": 925.1717356430731, "count": 36399, "self": 0.5078730520722274, "children": { "env_step": { "total": 924.6638625910009, "count": 36399, "self": 645.2641434810125, "children": { "SubprocessEnvManager._take_step": { "total": 278.8481764129092, "count": 36399, "self": 2.805793646903112, "children": { "TorchPolicy.evaluate": { "total": 276.0423827660061, "count": 36399, "self": 276.0423827660061 } } }, "workers": { "total": 0.551542697079185, "count": 36399, "self": 0.0, "children": { "worker_root": { "total": 927.374942489078, "count": 36399, "is_parallel": true, "self": 499.92885281904273, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005414814999767259, "count": 1, "is_parallel": true, "self": 0.003975891999289161, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014389230004780984, "count": 10, "is_parallel": true, "self": 0.0014389230004780984 } } }, "UnityEnvironment.step": { "total": 0.05925037599990901, "count": 1, "is_parallel": true, "self": 0.0006171290001475427, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000381070000003092, "count": 1, "is_parallel": true, "self": 0.000381070000003092 }, "communicator.exchange": { "total": 0.05633517399974153, "count": 1, "is_parallel": true, "self": 0.05633517399974153 }, "steps_from_proto": { "total": 0.001917003000016848, "count": 1, "is_parallel": true, "self": 0.000384973999189242, "children": { "_process_rank_one_or_two_observation": { "total": 0.001532029000827606, "count": 10, "is_parallel": true, "self": 0.001532029000827606 } } } } } } }, "UnityEnvironment.step": { "total": 427.44608967003524, "count": 36398, "is_parallel": true, "self": 20.59565269400673, "children": { "UnityEnvironment._generate_step_input": { "total": 10.535106480023387, "count": 36398, "is_parallel": true, "self": 10.535106480023387 }, "communicator.exchange": { "total": 330.9306253589798, "count": 36398, "is_parallel": true, "self": 330.9306253589798 }, "steps_from_proto": { "total": 65.38470513702532, "count": 36398, "is_parallel": true, "self": 11.962407448971135, "children": { "_process_rank_one_or_two_observation": { "total": 53.422297688054186, "count": 363980, "is_parallel": true, "self": 53.422297688054186 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00023636300011276035, "count": 1, "self": 0.00023636300011276035, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 914.36439917485, "count": 1308593, "is_parallel": true, "self": 27.35198290780636, "children": { "process_trajectory": { "total": 457.7374168880442, "count": 1308593, "is_parallel": true, "self": 456.86231000704356, "children": { "RLTrainer._checkpoint": { "total": 0.8751068810006473, "count": 8, "is_parallel": true, "self": 0.8751068810006473 } } }, "_update_policy": { "total": 429.2749993789994, "count": 181, "is_parallel": true, "self": 98.25419236201242, "children": { "TorchPPOOptimizer.update": { "total": 331.02080701698696, "count": 18459, "is_parallel": true, "self": 331.02080701698696 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12000034599986975, "count": 1, "self": 0.0008530370005246368, "children": { "RLTrainer._checkpoint": { "total": 0.11914730899934511, "count": 1, "self": 0.11914730899934511 } } } } } } }