{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9903283715248108, "min": 0.9903283715248108, "max": 2.863736867904663, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9477.4423828125, "min": 9477.4423828125, "max": 29390.53125, "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": 13.014819145202637, "min": 0.31013351678848267, "max": 13.014819145202637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2537.8896484375, "min": 60.1659049987793, "max": 2620.49609375, "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": 0.06810061547067188, "min": 0.05925920205510349, "max": 0.07225907318814494, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2724024618826875, "min": 0.23703680822041395, "max": 0.3612953659407247, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19339811363640952, "min": 0.12707621151097484, "max": 0.2883599231640498, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7735924545456381, "min": 0.5083048460438994, "max": 1.441799615820249, "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": 26.204545454545453, "min": 3.340909090909091, "max": 26.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1153.0, "min": 147.0, "max": 1419.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.204545454545453, "min": 3.340909090909091, "max": 26.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1153.0, "min": 147.0, "max": 1419.0, "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": "1702454712", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702455205" }, "total": 492.64067354400015, "count": 1, "self": 0.4529641110000284, "children": { "run_training.setup": { "total": 0.05763644600006046, "count": 1, "self": 0.05763644600006046 }, "TrainerController.start_learning": { "total": 492.13007298700006, "count": 1, "self": 0.5817882040080349, "children": { "TrainerController._reset_env": { "total": 3.3032332809999616, "count": 1, "self": 3.3032332809999616 }, "TrainerController.advance": { "total": 488.1324725929919, "count": 18206, "self": 0.2883338389849541, "children": { "env_step": { "total": 487.84413875400696, "count": 18206, "self": 329.0462526800046, "children": { "SubprocessEnvManager._take_step": { "total": 158.38597918899632, "count": 18206, "self": 1.5426564790041084, "children": { "TorchPolicy.evaluate": { "total": 156.8433227099922, "count": 18206, "self": 156.8433227099922 } } }, "workers": { "total": 0.411906885006033, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 490.70664189799174, "count": 18206, "is_parallel": true, "self": 238.35321332398928, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005609468999978162, "count": 1, "is_parallel": true, "self": 0.0041479529999151055, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014615160000630567, "count": 10, "is_parallel": true, "self": 0.0014615160000630567 } } }, "UnityEnvironment.step": { "total": 0.03806013900009475, "count": 1, "is_parallel": true, "self": 0.0007246860001259847, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036181999996642844, "count": 1, "is_parallel": true, "self": 0.00036181999996642844 }, "communicator.exchange": { "total": 0.03476451699998506, "count": 1, "is_parallel": true, "self": 0.03476451699998506 }, "steps_from_proto": { "total": 0.002209116000017275, "count": 1, "is_parallel": true, "self": 0.00045612200017330906, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017529939998439659, "count": 10, "is_parallel": true, "self": 0.0017529939998439659 } } } } } } }, "UnityEnvironment.step": { "total": 252.35342857400246, "count": 18205, "is_parallel": true, "self": 11.07321780899656, "children": { "UnityEnvironment._generate_step_input": { "total": 5.816220646005149, "count": 18205, "is_parallel": true, "self": 5.816220646005149 }, "communicator.exchange": { "total": 198.6258819219994, "count": 18205, "is_parallel": true, "self": 198.6258819219994 }, "steps_from_proto": { "total": 36.83810819700136, "count": 18205, "is_parallel": true, "self": 7.029631409968488, "children": { "_process_rank_one_or_two_observation": { "total": 29.808476787032873, "count": 182050, "is_parallel": true, "self": 29.808476787032873 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022419600009015994, "count": 1, "self": 0.00022419600009015994, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 483.8425781249563, "count": 516544, "is_parallel": true, "self": 11.721160204899775, "children": { "process_trajectory": { "total": 276.2851268660562, "count": 516544, "is_parallel": true, "self": 275.6323833920562, "children": { "RLTrainer._checkpoint": { "total": 0.6527434739999762, "count": 4, "is_parallel": true, "self": 0.6527434739999762 } } }, "_update_policy": { "total": 195.8362910540003, "count": 90, "is_parallel": true, "self": 56.121929460000274, "children": { "TorchPPOOptimizer.update": { "total": 139.71436159400002, "count": 4587, "is_parallel": true, "self": 139.71436159400002 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11235471300005884, "count": 1, "self": 0.0009484219999649213, "children": { "RLTrainer._checkpoint": { "total": 0.11140629100009392, "count": 1, "self": 0.11140629100009392 } } } } } } }