{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9363082647323608, "min": 0.9363082647323608, "max": 2.849673271179199, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8939.87109375, "min": 8939.87109375, "max": 29340.236328125, "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": 13.020767211914062, "min": 0.4478444755077362, "max": 13.031867980957031, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2539.049560546875, "min": 86.88182830810547, "max": 2658.5009765625, "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": 0.06489654400010134, "min": 0.05839584106762036, "max": 0.07423634865606836, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25958617600040534, "min": 0.23358336427048143, "max": 0.36551048351305093, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22265557462678237, "min": 0.14362159118229778, "max": 0.28818125087840885, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8906222985071295, "min": 0.5744863647291911, "max": 1.3765461300956268, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "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": 25.15909090909091, "min": 3.6818181818181817, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 162.0, "max": 1418.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.6818181818181817, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 162.0, "max": 1418.0, "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": "1705854082", "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/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget6 --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": "1705854549" }, "total": 466.9953656920002, "count": 1, "self": 0.4372544780003409, "children": { "run_training.setup": { "total": 0.07444663199976276, "count": 1, "self": 0.07444663199976276 }, "TrainerController.start_learning": { "total": 466.4836645820001, "count": 1, "self": 0.5818096489674645, "children": { "TrainerController._reset_env": { "total": 3.0569892759999675, "count": 1, "self": 3.0569892759999675 }, "TrainerController.advance": { "total": 462.7485700340326, "count": 18200, "self": 0.27301944102100606, "children": { "env_step": { "total": 462.4755505930116, "count": 18200, "self": 304.81237759906116, "children": { "SubprocessEnvManager._take_step": { "total": 157.3706781550136, "count": 18200, "self": 1.5090432449865148, "children": { "TorchPolicy.evaluate": { "total": 155.86163491002708, "count": 18200, "self": 155.86163491002708 } } }, "workers": { "total": 0.29249483893681827, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 465.184047372024, "count": 18200, "is_parallel": true, "self": 228.6064905760427, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0042291820000173175, "count": 1, "is_parallel": true, "self": 0.00282668699946953, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014024950005477876, "count": 10, "is_parallel": true, "self": 0.0014024950005477876 } } }, "UnityEnvironment.step": { "total": 0.03922871499980829, "count": 1, "is_parallel": true, "self": 0.0007144319997678394, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037762300007671, "count": 1, "is_parallel": true, "self": 0.00037762300007671 }, "communicator.exchange": { "total": 0.03589437699974951, "count": 1, "is_parallel": true, "self": 0.03589437699974951 }, "steps_from_proto": { "total": 0.002242283000214229, "count": 1, "is_parallel": true, "self": 0.0006011460004629043, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016411369997513248, "count": 10, "is_parallel": true, "self": 0.0016411369997513248 } } } } } } }, "UnityEnvironment.step": { "total": 236.5775567959813, "count": 18199, "is_parallel": true, "self": 10.731102176972854, "children": { "UnityEnvironment._generate_step_input": { "total": 5.578069799966215, "count": 18199, "is_parallel": true, "self": 5.578069799966215 }, "communicator.exchange": { "total": 184.86139338899648, "count": 18199, "is_parallel": true, "self": 184.86139338899648 }, "steps_from_proto": { "total": 35.406991430045764, "count": 18199, "is_parallel": true, "self": 6.688201076011865, "children": { "_process_rank_one_or_two_observation": { "total": 28.7187903540339, "count": 181990, "is_parallel": true, "self": 28.7187903540339 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014662200010207016, "count": 1, "self": 0.00014662200010207016, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.5014794541762, "count": 605664, "is_parallel": true, "self": 13.870974575075707, "children": { "process_trajectory": { "total": 256.0502185271007, "count": 605664, "is_parallel": true, "self": 255.08174741110088, "children": { "RLTrainer._checkpoint": { "total": 0.9684711159998187, "count": 4, "is_parallel": true, "self": 0.9684711159998187 } } }, "_update_policy": { "total": 187.5802863519998, "count": 90, "is_parallel": true, "self": 57.158695915996304, "children": { "TorchPPOOptimizer.update": { "total": 130.4215904360035, "count": 4584, "is_parallel": true, "self": 130.4215904360035 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09614900099995793, "count": 1, "self": 0.001074066999990464, "children": { "RLTrainer._checkpoint": { "total": 0.09507493399996747, "count": 1, "self": 0.09507493399996747 } } } } } } }