{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8586149215698242, "min": 0.8586149215698242, "max": 2.850626230239868, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8160.2763671875, "min": 8160.2763671875, "max": 29099.19140625, "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": 12.993285179138184, "min": 0.4486110806465149, "max": 12.993285179138184, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2533.690673828125, "min": 87.03054809570312, "max": 2638.14013671875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07178388990723761, "min": 0.06347253854790538, "max": 0.07186159303528258, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28713555962895043, "min": 0.25389015419162153, "max": 0.3593079651764129, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.187084013267475, "min": 0.12206369647801874, "max": 0.3099500854663989, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7483360530699, "min": 0.48825478591207494, "max": 1.4367218788932352, "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.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.Environment.CumulativeReward.mean": { "value": 25.431818181818183, "min": 3.5454545454545454, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 156.0, "max": 1417.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.5454545454545454, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 156.0, "max": 1417.0, "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": "1776776111", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1776776567" }, "total": 455.81092892799984, "count": 1, "self": 0.42901224499996715, "children": { "run_training.setup": { "total": 0.02288633399984974, "count": 1, "self": 0.02288633399984974 }, "TrainerController.start_learning": { "total": 455.359030349, "count": 1, "self": 0.383556971022017, "children": { "TrainerController._reset_env": { "total": 2.212020356000039, "count": 1, "self": 2.212020356000039 }, "TrainerController.advance": { "total": 452.68226949197833, "count": 18192, "self": 0.37395584389491887, "children": { "env_step": { "total": 330.58746128503367, "count": 18192, "self": 258.07750531612965, "children": { "SubprocessEnvManager._take_step": { "total": 72.2932843179301, "count": 18192, "self": 1.3273167099257535, "children": { "TorchPolicy.evaluate": { "total": 70.96596760800435, "count": 18192, "self": 70.96596760800435 } } }, "workers": { "total": 0.21667165097392171, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 453.4772613789603, "count": 18192, "is_parallel": true, "self": 226.606193148996, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020802809999622696, "count": 1, "is_parallel": true, "self": 0.0006262690001221927, "children": { "_process_rank_one_or_two_observation": { "total": 0.001454011999840077, "count": 10, "is_parallel": true, "self": 0.001454011999840077 } } }, "UnityEnvironment.step": { "total": 0.0773338059998423, "count": 1, "is_parallel": true, "self": 0.002659708999999566, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004202349998649879, "count": 1, "is_parallel": true, "self": 0.0004202349998649879 }, "communicator.exchange": { "total": 0.06826789000001554, "count": 1, "is_parallel": true, "self": 0.06826789000001554 }, "steps_from_proto": { "total": 0.005985971999962203, "count": 1, "is_parallel": true, "self": 0.004435548000174094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015504239997881086, "count": 10, "is_parallel": true, "self": 0.0015504239997881086 } } } } } } }, "UnityEnvironment.step": { "total": 226.8710682299643, "count": 18191, "is_parallel": true, "self": 10.459219316909412, "children": { "UnityEnvironment._generate_step_input": { "total": 5.568849922010713, "count": 18191, "is_parallel": true, "self": 5.568849922010713 }, "communicator.exchange": { "total": 172.77319669901135, "count": 18191, "is_parallel": true, "self": 172.77319669901135 }, "steps_from_proto": { "total": 38.06980229203282, "count": 18191, "is_parallel": true, "self": 6.867730376072586, "children": { "_process_rank_one_or_two_observation": { "total": 31.202071915960232, "count": 181910, "is_parallel": true, "self": 31.202071915960232 } } } } } } } } } } }, "trainer_advance": { "total": 121.72085236304974, "count": 18192, "self": 0.4428068310664912, "children": { "process_trajectory": { "total": 27.330043215984006, "count": 18192, "self": 26.819191248983998, "children": { "RLTrainer._checkpoint": { "total": 0.5108519670000078, "count": 4, "self": 0.5108519670000078 } } }, "_update_policy": { "total": 93.94800231599925, "count": 90, "self": 38.06931249600416, "children": { "TorchPPOOptimizer.update": { "total": 55.87868981999509, "count": 4587, "self": 55.87868981999509 } } } } } } }, "trainer_threads": { "total": 1.0469998414919246e-06, "count": 1, "self": 1.0469998414919246e-06 }, "TrainerController._save_models": { "total": 0.08118248299979314, "count": 1, "self": 0.000961086999723193, "children": { "RLTrainer._checkpoint": { "total": 0.08022139600006994, "count": 1, "self": 0.08022139600006994 } } } } } } }