{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7475182414054871, "min": 0.71663498878479, "max": 2.8489346504211426, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7104.4130859375, "min": 6810.89892578125, "max": 29081.923828125, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.4374361038208, "min": 0.394808828830719, "max": 13.4374361038208, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2606.862548828125, "min": 76.59291076660156, "max": 2735.1162109375, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.071493054551812, "min": 0.06355938853156141, "max": 0.07763451731960089, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.285972218207248, "min": 0.25423755412624566, "max": 0.3881725865980044, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17382255499707716, "min": 0.14108746513203882, "max": 0.2882686865095998, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6952902199883086, "min": 0.5643498605281553, "max": 1.3754066886270748, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.91520980848e-05, "min": 1.91520980848e-05, "max": 0.0009783520021647998, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 7.66083923392e-05, "min": 7.66083923392e-05, "max": 0.004693760030624001, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10229824, "min": 0.10229824, "max": 0.21740224, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40919296, "min": 0.40919296, "max": 1.0632512, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00012472048000000002, "min": 0.00012472048000000002, "max": 0.005870328480000001, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004988819200000001, "min": 0.0004988819200000001, "max": 0.0281656224, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.477272727272727, "min": 3.772727272727273, "max": 26.636363636363637, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1165.0, "min": 166.0, "max": 1465.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.477272727272727, "min": 3.772727272727273, "max": 26.636363636363637, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1165.0, "min": 166.0, "max": 1465.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1767977742", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./SnowballTarget.yaml --env=../../training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "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": "1767978274" }, "total": 532.3112778719997, "count": 1, "self": 0.4286831940007687, "children": { "run_training.setup": { "total": 0.024501590999534528, "count": 1, "self": 0.024501590999534528 }, "TrainerController.start_learning": { "total": 531.8580930869994, "count": 1, "self": 0.4673537579665208, "children": { "TrainerController._reset_env": { "total": 2.4818936770006985, "count": 1, "self": 2.4818936770006985 }, "TrainerController.advance": { "total": 528.8332635740326, "count": 22728, "self": 0.4606399049689571, "children": { "env_step": { "total": 381.6540236930405, "count": 22728, "self": 298.851979642106, "children": { "SubprocessEnvManager._take_step": { "total": 82.53021616796832, "count": 22728, "self": 1.568552725923837, "children": { "TorchPolicy.evaluate": { "total": 80.96166344204448, "count": 22728, "self": 80.96166344204448 } } }, "workers": { "total": 0.2718278829661358, "count": 22728, "self": 0.0, "children": { "worker_root": { "total": 529.6468840889474, "count": 22728, "is_parallel": true, "self": 267.56324332680924, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002008778000345046, "count": 1, "is_parallel": true, "self": 0.0006225420020200545, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013862359983249917, "count": 10, "is_parallel": true, "self": 0.0013862359983249917 } } }, "UnityEnvironment.step": { "total": 0.06370068799969886, "count": 1, "is_parallel": true, "self": 0.0012191709993203403, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038346000019373605, "count": 1, "is_parallel": true, "self": 0.00038346000019373605 }, "communicator.exchange": { "total": 0.05938122600036877, "count": 1, "is_parallel": true, "self": 0.05938122600036877 }, "steps_from_proto": { "total": 0.002716830999816011, "count": 1, "is_parallel": true, "self": 0.0003291299999546027, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023877009998614085, "count": 10, "is_parallel": true, "self": 0.0023877009998614085 } } } } } } }, "UnityEnvironment.step": { "total": 262.0836407621382, "count": 22727, "is_parallel": true, "self": 12.365990891184083, "children": { "UnityEnvironment._generate_step_input": { "total": 6.582015843963745, "count": 22727, "is_parallel": true, "self": 6.582015843963745 }, "communicator.exchange": { "total": 200.4483943029445, "count": 22727, "is_parallel": true, "self": 200.4483943029445 }, "steps_from_proto": { "total": 42.68723972404587, "count": 22727, "is_parallel": true, "self": 7.9181404071123325, "children": { "_process_rank_one_or_two_observation": { "total": 34.769099316933534, "count": 227270, "is_parallel": true, "self": 34.769099316933534 } } } } } } } } } } }, "trainer_advance": { "total": 146.71859997602314, "count": 22728, "self": 0.6203085009537972, "children": { "process_trajectory": { "total": 31.306125940061975, "count": 22728, "self": 30.834229514061917, "children": { "RLTrainer._checkpoint": { "total": 0.47189642600005755, "count": 5, "self": 0.47189642600005755 } } }, "_update_policy": { "total": 114.79216553500737, "count": 113, "self": 46.65109521096747, "children": { "TorchPPOOptimizer.update": { "total": 68.1410703240399, "count": 5760, "self": 68.1410703240399 } } } } } } }, "trainer_threads": { "total": 1.014999725157395e-06, "count": 1, "self": 1.014999725157395e-06 }, "TrainerController._save_models": { "total": 0.07558106299984502, "count": 1, "self": 0.000854279000122915, "children": { "RLTrainer._checkpoint": { "total": 0.0747267839997221, "count": 1, "self": 0.0747267839997221 } } } } } } }