{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9422412514686584, "min": 0.9422412514686584, "max": 2.8664231300354004, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8996.51953125, "min": 8996.51953125, "max": 29418.1015625, "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": 12.755426406860352, "min": 0.3794362246990204, "max": 12.755426406860352, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2487.30810546875, "min": 73.61062622070312, "max": 2554.177734375, "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": 0.0635759476184224, "min": 0.06257579988153998, "max": 0.07587045722888719, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2543037904736896, "min": 0.2503031995261599, "max": 0.35930167196299106, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22818079554274973, "min": 0.10669318321343584, "max": 0.2895609795608941, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9127231821709989, "min": 0.42677273285374334, "max": 1.382171713254031, "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": 25.545454545454547, "min": 3.2954545454545454, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1124.0, "min": 145.0, "max": 1370.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.545454545454547, "min": 3.2954545454545454, "max": 25.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1124.0, "min": 145.0, "max": 1370.0, "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": "1679318884", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679319358" }, "total": 474.1336049300003, "count": 1, "self": 0.44009861300082775, "children": { "run_training.setup": { "total": 0.10474744799967084, "count": 1, "self": 0.10474744799967084 }, "TrainerController.start_learning": { "total": 473.5887588689998, "count": 1, "self": 0.5665627350003888, "children": { "TrainerController._reset_env": { "total": 8.395298228000229, "count": 1, "self": 8.395298228000229 }, "TrainerController.advance": { "total": 464.4802571139994, "count": 18201, "self": 0.30488606099243043, "children": { "env_step": { "total": 464.175371053007, "count": 18201, "self": 331.02882855100825, "children": { "SubprocessEnvManager._take_step": { "total": 132.86095986002965, "count": 18201, "self": 1.9866540410271227, "children": { "TorchPolicy.evaluate": { "total": 130.87430581900253, "count": 18201, "self": 130.87430581900253 } } }, "workers": { "total": 0.28558264196908567, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 472.0981763350119, "count": 18201, "is_parallel": true, "self": 226.85456594302605, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005014638000375271, "count": 1, "is_parallel": true, "self": 0.003511779999371356, "children": { "_process_rank_one_or_two_observation": { "total": 0.001502858001003915, "count": 10, "is_parallel": true, "self": 0.001502858001003915 } } }, "UnityEnvironment.step": { "total": 0.05999726500022007, "count": 1, "is_parallel": true, "self": 0.0006575510001312068, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036095299992666696, "count": 1, "is_parallel": true, "self": 0.00036095299992666696 }, "communicator.exchange": { "total": 0.05704352500015375, "count": 1, "is_parallel": true, "self": 0.05704352500015375 }, "steps_from_proto": { "total": 0.0019352360000084445, "count": 1, "is_parallel": true, "self": 0.00038361299948519445, "children": { "_process_rank_one_or_two_observation": { "total": 0.00155162300052325, "count": 10, "is_parallel": true, "self": 0.00155162300052325 } } } } } } }, "UnityEnvironment.step": { "total": 245.24361039198584, "count": 18200, "is_parallel": true, "self": 9.71383036793668, "children": { "UnityEnvironment._generate_step_input": { "total": 5.381093901034546, "count": 18200, "is_parallel": true, "self": 5.381093901034546 }, "communicator.exchange": { "total": 197.00245327702442, "count": 18200, "is_parallel": true, "self": 197.00245327702442 }, "steps_from_proto": { "total": 33.1462328459902, "count": 18200, "is_parallel": true, "self": 6.711429257994041, "children": { "_process_rank_one_or_two_observation": { "total": 26.434803587996157, "count": 182000, "is_parallel": true, "self": 26.434803587996157 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013724099972023396, "count": 1, "self": 0.00013724099972023396, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 460.782650840119, "count": 423871, "is_parallel": true, "self": 10.91858612734859, "children": { "process_trajectory": { "total": 258.4001306387713, "count": 423871, "is_parallel": true, "self": 257.5405520917716, "children": { "RLTrainer._checkpoint": { "total": 0.8595785469997281, "count": 4, "is_parallel": true, "self": 0.8595785469997281 } } }, "_update_policy": { "total": 191.4639340739991, "count": 90, "is_parallel": true, "self": 69.95742427200184, "children": { "TorchPPOOptimizer.update": { "total": 121.50650980199725, "count": 4584, "is_parallel": true, "self": 121.50650980199725 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14650355100002344, "count": 1, "self": 0.000982899000064208, "children": { "RLTrainer._checkpoint": { "total": 0.14552065199995923, "count": 1, "self": 0.14552065199995923 } } } } } } }