{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9831191897392273, "min": 0.9831191897392273, "max": 2.875648021697998, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9386.822265625, "min": 9386.822265625, "max": 29481.14453125, "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": 12.891549110412598, "min": 0.3905321955680847, "max": 12.891549110412598, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2513.85205078125, "min": 75.76324462890625, "max": 2627.29833984375, "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": 0.06837162955070215, "min": 0.06239064517033994, "max": 0.07187704123218783, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2734865182028086, "min": 0.24956258068135975, "max": 0.3593852061609391, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19675974843694885, "min": 0.12199170696868689, "max": 0.29686008474113895, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7870389937477954, "min": 0.48796682787474754, "max": 1.4843004237056947, "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": 25.0, "min": 3.6363636363636362, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 160.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.6363636363636362, "max": 25.236363636363638, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 160.0, "max": 1388.0, "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": "1696278951", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1696279409" }, "total": 458.45095182299997, "count": 1, "self": 0.4331676959999413, "children": { "run_training.setup": { "total": 0.05107429500003491, "count": 1, "self": 0.05107429500003491 }, "TrainerController.start_learning": { "total": 457.966709832, "count": 1, "self": 0.4855745950094388, "children": { "TrainerController._reset_env": { "total": 4.030715110000074, "count": 1, "self": 4.030715110000074 }, "TrainerController.advance": { "total": 453.31051555099054, "count": 18201, "self": 0.23878693998494782, "children": { "env_step": { "total": 453.0717286110056, "count": 18201, "self": 332.4969020440192, "children": { "SubprocessEnvManager._take_step": { "total": 120.32123669200143, "count": 18201, "self": 1.595644410999057, "children": { "TorchPolicy.evaluate": { "total": 118.72559228100238, "count": 18201, "self": 118.72559228100238 } } }, "workers": { "total": 0.2535898749849821, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 456.5246283950099, "count": 18201, "is_parallel": true, "self": 216.68626813499816, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005505009999978938, "count": 1, "is_parallel": true, "self": 0.003932947000066633, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015720629999123048, "count": 10, "is_parallel": true, "self": 0.0015720629999123048 } } }, "UnityEnvironment.step": { "total": 0.034720041000014135, "count": 1, "is_parallel": true, "self": 0.0006562949999988632, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003178709999929197, "count": 1, "is_parallel": true, "self": 0.0003178709999929197 }, "communicator.exchange": { "total": 0.030503574000022127, "count": 1, "is_parallel": true, "self": 0.030503574000022127 }, "steps_from_proto": { "total": 0.003242301000000225, "count": 1, "is_parallel": true, "self": 0.00046628100017187535, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027760199998283497, "count": 10, "is_parallel": true, "self": 0.0027760199998283497 } } } } } } }, "UnityEnvironment.step": { "total": 239.83836026001177, "count": 18200, "is_parallel": true, "self": 10.300161253010629, "children": { "UnityEnvironment._generate_step_input": { "total": 5.164958597008763, "count": 18200, "is_parallel": true, "self": 5.164958597008763 }, "communicator.exchange": { "total": 189.45734801799983, "count": 18200, "is_parallel": true, "self": 189.45734801799983 }, "steps_from_proto": { "total": 34.91589239199254, "count": 18200, "is_parallel": true, "self": 6.216417164000404, "children": { "_process_rank_one_or_two_observation": { "total": 28.69947522799214, "count": 182000, "is_parallel": true, "self": 28.69947522799214 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012736999997287057, "count": 1, "self": 0.00012736999997287057, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 449.89188196511543, "count": 418408, "is_parallel": true, "self": 9.647162718113691, "children": { "process_trajectory": { "total": 243.35068425100224, "count": 418408, "is_parallel": true, "self": 241.9882054890022, "children": { "RLTrainer._checkpoint": { "total": 1.3624787620000234, "count": 4, "is_parallel": true, "self": 1.3624787620000234 } } }, "_update_policy": { "total": 196.8940349959995, "count": 90, "is_parallel": true, "self": 80.72395519200006, "children": { "TorchPPOOptimizer.update": { "total": 116.17007980399944, "count": 4584, "is_parallel": true, "self": 116.17007980399944 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13977720599996246, "count": 1, "self": 0.000868006000018795, "children": { "RLTrainer._checkpoint": { "total": 0.13890919999994367, "count": 1, "self": 0.13890919999994367 } } } } } } }