{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9842599034309387, "min": 0.9842599034309387, "max": 2.8565762042999268, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9505.982421875, "min": 9505.982421875, "max": 29254.197265625, "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": 12.958781242370605, "min": 0.3143642544746399, "max": 12.958781242370605, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.96240234375, "min": 60.986663818359375, "max": 2620.310791015625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0448428962493684, "min": 0.04293987233965406, "max": 0.05509057771674482, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.1793715849974736, "min": 0.17175948935861624, "max": 0.2726525212977625, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17427400150336325, "min": 0.10611772273356715, "max": 0.3169617368839681, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.697096006013453, "min": 0.4244708909342686, "max": 1.5002638523777327, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.00029188200270599996, "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": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014443060000000012, "min": 0.00014443060000000012, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000005, "min": 0.0005777224000000005, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.704545454545453, "min": 2.8181818181818183, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1131.0, "min": 124.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.704545454545453, "min": 2.8181818181818183, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1131.0, "min": 124.0, "max": 1402.0, "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": "1677951961", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677952398" }, "total": 437.77440453199995, "count": 1, "self": 0.756814463000012, "children": { "run_training.setup": { "total": 0.12253315499998507, "count": 1, "self": 0.12253315499998507 }, "TrainerController.start_learning": { "total": 436.89505691399995, "count": 1, "self": 0.5208468710017087, "children": { "TrainerController._reset_env": { "total": 10.245719038999994, "count": 1, "self": 10.245719038999994 }, "TrainerController.advance": { "total": 425.9040841969982, "count": 18235, "self": 0.27590179899766554, "children": { "env_step": { "total": 425.62818239800055, "count": 18235, "self": 284.0018868759949, "children": { "SubprocessEnvManager._take_step": { "total": 141.35620788000483, "count": 18235, "self": 1.4616089900050042, "children": { "TorchPolicy.evaluate": { "total": 139.89459888999983, "count": 18235, "self": 31.25373147300928, "children": { "TorchPolicy.sample_actions": { "total": 108.64086741699055, "count": 18235, "self": 108.64086741699055 } } } } }, "workers": { "total": 0.27008764200081714, "count": 18235, "self": 0.0, "children": { "worker_root": { "total": 435.26935281999863, "count": 18235, "is_parallel": true, "self": 204.99056556500568, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005276578999996673, "count": 1, "is_parallel": true, "self": 0.003882651999845166, "children": { "_process_rank_one_or_two_observation": { "total": 0.001393927000151507, "count": 10, "is_parallel": true, "self": 0.001393927000151507 } } }, "UnityEnvironment.step": { "total": 0.04308472399998209, "count": 1, "is_parallel": true, "self": 0.0005460680000055618, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023904899995841333, "count": 1, "is_parallel": true, "self": 0.00023904899995841333 }, "communicator.exchange": { "total": 0.040561442000011994, "count": 1, "is_parallel": true, "self": 0.040561442000011994 }, "steps_from_proto": { "total": 0.00173816500000612, "count": 1, "is_parallel": true, "self": 0.0004306960000235449, "children": { "_process_rank_one_or_two_observation": { "total": 0.001307468999982575, "count": 10, "is_parallel": true, "self": 0.001307468999982575 } } } } } } }, "UnityEnvironment.step": { "total": 230.27878725499295, "count": 18234, "is_parallel": true, "self": 9.374886687972719, "children": { "UnityEnvironment._generate_step_input": { "total": 5.1205250040074475, "count": 18234, "is_parallel": true, "self": 5.1205250040074475 }, "communicator.exchange": { "total": 185.88453295001483, "count": 18234, "is_parallel": true, "self": 185.88453295001483 }, "steps_from_proto": { "total": 29.898842612997953, "count": 18234, "is_parallel": true, "self": 6.481986660980738, "children": { "_process_rank_one_or_two_observation": { "total": 23.416855952017215, "count": 182340, "is_parallel": true, "self": 23.416855952017215 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001538180000579814, "count": 1, "self": 0.0001538180000579814, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 422.2492499630004, "count": 430431, "is_parallel": true, "self": 10.675431278012809, "children": { "process_trajectory": { "total": 272.2493751029868, "count": 430431, "is_parallel": true, "self": 270.34449438798674, "children": { "RLTrainer._checkpoint": { "total": 1.904880715000047, "count": 4, "is_parallel": true, "self": 1.904880715000047 } } }, "_update_policy": { "total": 139.3244435820008, "count": 90, "is_parallel": true, "self": 65.4387543959997, "children": { "TorchPPOOptimizer.update": { "total": 73.88568918600112, "count": 2160, "is_parallel": true, "self": 73.88568918600112 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2242529889999787, "count": 1, "self": 0.002236612999922727, "children": { "RLTrainer._checkpoint": { "total": 0.22201637600005597, "count": 1, "self": 0.22201637600005597 } } } } } } }