{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8692570924758911, "min": 0.8692570924758911, "max": 2.8648226261138916, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8299.6669921875, "min": 8299.6669921875, "max": 29401.67578125, "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": 12.510869979858398, "min": 0.2526598274707794, "max": 12.510869979858398, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2439.61962890625, "min": 49.01600646972656, "max": 2506.46142578125, "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": 0.06309229772630394, "min": 0.06309229772630394, "max": 0.07428013085885266, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25236919090521576, "min": 0.25236919090521576, "max": 0.3714006542942633, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21320598901194684, "min": 0.10563477121953231, "max": 0.2945316406879939, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8528239560477874, "min": 0.42253908487812925, "max": 1.391874379387089, "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": 2.7954545454545454, "max": 25.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 123.0, "max": 1358.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 2.7954545454545454, "max": 25.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 123.0, "max": 1358.0, "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": "1718341994", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718342436" }, "total": 441.62311799300005, "count": 1, "self": 0.39074076599990804, "children": { "run_training.setup": { "total": 0.061756705000107104, "count": 1, "self": 0.061756705000107104 }, "TrainerController.start_learning": { "total": 441.17062052200004, "count": 1, "self": 0.5506801079802699, "children": { "TrainerController._reset_env": { "total": 3.030753963000052, "count": 1, "self": 3.030753963000052 }, "TrainerController.advance": { "total": 437.49497502001987, "count": 18200, "self": 0.2722171890241043, "children": { "env_step": { "total": 437.22275783099576, "count": 18200, "self": 284.07631011499734, "children": { "SubprocessEnvManager._take_step": { "total": 152.87177889499776, "count": 18200, "self": 1.447883548002892, "children": { "TorchPolicy.evaluate": { "total": 151.42389534699487, "count": 18200, "self": 151.42389534699487 } } }, "workers": { "total": 0.2746688210006596, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 439.9190876180119, "count": 18200, "is_parallel": true, "self": 224.37016951901182, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006014651999976195, "count": 1, "is_parallel": true, "self": 0.004366218999393823, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016484330005823722, "count": 10, "is_parallel": true, "self": 0.0016484330005823722 } } }, "UnityEnvironment.step": { "total": 0.03770625900006053, "count": 1, "is_parallel": true, "self": 0.0006576179998774023, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040837500000634464, "count": 1, "is_parallel": true, "self": 0.00040837500000634464 }, "communicator.exchange": { "total": 0.03472916000009718, "count": 1, "is_parallel": true, "self": 0.03472916000009718 }, "steps_from_proto": { "total": 0.0019111060000795987, "count": 1, "is_parallel": true, "self": 0.00038390000031540694, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015272059997641918, "count": 10, "is_parallel": true, "self": 0.0015272059997641918 } } } } } } }, "UnityEnvironment.step": { "total": 215.54891809900005, "count": 18199, "is_parallel": true, "self": 9.960079741998015, "children": { "UnityEnvironment._generate_step_input": { "total": 5.197135898999932, "count": 18199, "is_parallel": true, "self": 5.197135898999932 }, "communicator.exchange": { "total": 167.97616892399037, "count": 18199, "is_parallel": true, "self": 167.97616892399037 }, "steps_from_proto": { "total": 32.41553353401173, "count": 18199, "is_parallel": true, "self": 6.071559160003062, "children": { "_process_rank_one_or_two_observation": { "total": 26.343974374008667, "count": 181990, "is_parallel": true, "self": 26.343974374008667 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001253670000096463, "count": 1, "self": 0.0001253670000096463, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 432.35594080104374, "count": 661035, "is_parallel": true, "self": 13.330876432906052, "children": { "process_trajectory": { "total": 238.16402047713837, "count": 661035, "is_parallel": true, "self": 237.52794714513834, "children": { "RLTrainer._checkpoint": { "total": 0.6360733320000236, "count": 4, "is_parallel": true, "self": 0.6360733320000236 } } }, "_update_policy": { "total": 180.86104389099933, "count": 90, "is_parallel": true, "self": 60.01291836499604, "children": { "TorchPPOOptimizer.update": { "total": 120.84812552600329, "count": 4587, "is_parallel": true, "self": 120.84812552600329 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0940860639998391, "count": 1, "self": 0.0009630959998503386, "children": { "RLTrainer._checkpoint": { "total": 0.09312296799998876, "count": 1, "self": 0.09312296799998876 } } } } } } }