{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0261993408203125, "min": 1.0261993408203125, "max": 2.872718095779419, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9809.439453125, "min": 9809.439453125, "max": 29482.705078125, "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": 12.92346477508545, "min": 0.12713199853897095, "max": 12.92346477508545, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2520.07568359375, "min": 24.663606643676758, "max": 2579.058349609375, "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": 0.07676010337679912, "min": 0.060421812586123544, "max": 0.07676010337679912, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30704041350719646, "min": 0.24168725034449418, "max": 0.3573918371602856, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2140618260292446, "min": 0.1119084633697354, "max": 0.2760752454107883, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8562473041169784, "min": 0.4476338534789416, "max": 1.3715991328159967, "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": 25.795454545454547, "min": 3.340909090909091, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1135.0, "min": 147.0, "max": 1413.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.795454545454547, "min": 3.340909090909091, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1135.0, "min": 147.0, "max": 1413.0, "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": "1717532508", "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=./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": "1717532981" }, "total": 473.216795607, "count": 1, "self": 0.4364942769999516, "children": { "run_training.setup": { "total": 0.07448850600007972, "count": 1, "self": 0.07448850600007972 }, "TrainerController.start_learning": { "total": 472.70581282399996, "count": 1, "self": 0.6061174930094921, "children": { "TrainerController._reset_env": { "total": 2.8313272430000325, "count": 1, "self": 2.8313272430000325 }, "TrainerController.advance": { "total": 469.17779338199034, "count": 18201, "self": 0.29029719998436576, "children": { "env_step": { "total": 468.887496182006, "count": 18201, "self": 302.6693928240154, "children": { "SubprocessEnvManager._take_step": { "total": 165.90822031599475, "count": 18201, "self": 1.578496944003632, "children": { "TorchPolicy.evaluate": { "total": 164.32972337199112, "count": 18201, "self": 164.32972337199112 } } }, "workers": { "total": 0.3098830419958176, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 471.4421896859857, "count": 18201, "is_parallel": true, "self": 237.66894148097447, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005585879000022942, "count": 1, "is_parallel": true, "self": 0.003945888000203013, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016399909998199291, "count": 10, "is_parallel": true, "self": 0.0016399909998199291 } } }, "UnityEnvironment.step": { "total": 0.037593293999975685, "count": 1, "is_parallel": true, "self": 0.0006396909999466516, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003854200000432684, "count": 1, "is_parallel": true, "self": 0.0003854200000432684 }, "communicator.exchange": { "total": 0.03448506600000201, "count": 1, "is_parallel": true, "self": 0.03448506600000201 }, "steps_from_proto": { "total": 0.0020831169999837584, "count": 1, "is_parallel": true, "self": 0.0003906570001390719, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016924599998446865, "count": 10, "is_parallel": true, "self": 0.0016924599998446865 } } } } } } }, "UnityEnvironment.step": { "total": 233.7732482050112, "count": 18200, "is_parallel": true, "self": 10.659878812007719, "children": { "UnityEnvironment._generate_step_input": { "total": 5.685974720990998, "count": 18200, "is_parallel": true, "self": 5.685974720990998 }, "communicator.exchange": { "total": 181.77634375501464, "count": 18200, "is_parallel": true, "self": 181.77634375501464 }, "steps_from_proto": { "total": 35.65105091699786, "count": 18200, "is_parallel": true, "self": 6.859689688993967, "children": { "_process_rank_one_or_two_observation": { "total": 28.791361228003893, "count": 182000, "is_parallel": true, "self": 28.791361228003893 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011891600001945335, "count": 1, "self": 0.00011891600001945335, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 463.206403839979, "count": 706832, "is_parallel": true, "self": 15.289406107964624, "children": { "process_trajectory": { "total": 258.0627129420146, "count": 706832, "is_parallel": true, "self": 256.9375924600147, "children": { "RLTrainer._checkpoint": { "total": 1.125120481999943, "count": 4, "is_parallel": true, "self": 1.125120481999943 } } }, "_update_policy": { "total": 189.85428478999972, "count": 90, "is_parallel": true, "self": 58.1745490800032, "children": { "TorchPPOOptimizer.update": { "total": 131.67973570999652, "count": 4584, "is_parallel": true, "self": 131.67973570999652 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0904557900000782, "count": 1, "self": 0.0009112459999869316, "children": { "RLTrainer._checkpoint": { "total": 0.08954454400009126, "count": 1, "self": 0.08954454400009126 } } } } } } }