{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 1.3782317638397217, "min": 1.3782317638397217, "max": 1.418938398361206, "count": 33 }, "Worm.Policy.Entropy.sum": { "value": 41346.953125, "min": 41346.953125, "max": 42568.15234375, "count": 33 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 33 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 33 }, "Worm.Step.mean": { "value": 989000.0, "min": 29000.0, "max": 989000.0, "count": 33 }, "Worm.Step.sum": { "value": 989000.0, "min": 29000.0, "max": 989000.0, "count": 33 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 12.1596097946167, "min": -0.0510314404964447, "max": 12.1596097946167, "count": 33 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 364.7882995605469, "min": -1.4799118041992188, "max": 364.7882995605469, "count": 33 }, "Worm.Environment.CumulativeReward.mean": { "value": 104.5875857035319, "min": 0.23851448661198132, "max": 104.5875857035319, "count": 33 }, "Worm.Environment.CumulativeReward.sum": { "value": 3137.627571105957, "min": 6.916920111747459, "max": 3137.627571105957, "count": 33 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 104.5875857035319, "min": 0.23851448661198132, "max": 104.5875857035319, "count": 33 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 3137.627571105957, "min": 6.916920111747459, "max": 3137.627571105957, "count": 33 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.01622896203965259, "min": 0.012956498960279748, "max": 0.021438278102626402, "count": 32 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.01622896203965259, "min": 0.012956498960279748, "max": 0.021438278102626402, "count": 32 }, "Worm.Losses.ValueLoss.mean": { "value": 0.9577527798357464, "min": 0.002089883572244573, "max": 1.0014386361553556, "count": 32 }, "Worm.Losses.ValueLoss.sum": { "value": 0.9577527798357464, "min": 0.002089883572244573, "max": 1.0014386361553556, "count": 32 }, "Worm.Policy.LearningRate.mean": { "value": 1.2000096000000011e-05, "min": 1.2000096000000011e-05, "max": 0.0002910000029999999, "count": 32 }, "Worm.Policy.LearningRate.sum": { "value": 1.2000096000000011e-05, "min": 1.2000096000000011e-05, "max": 0.0002910000029999999, "count": 32 }, "Worm.Policy.Epsilon.mean": { "value": 0.10400000000000001, "min": 0.10400000000000001, "max": 0.19699999999999998, "count": 32 }, "Worm.Policy.Epsilon.sum": { "value": 0.10400000000000001, "min": 0.10400000000000001, "max": 0.19699999999999998, "count": 32 }, "Worm.Policy.Beta.mean": { "value": 0.00020960000000000022, "min": 0.00020960000000000022, "max": 0.0048503, "count": 32 }, "Worm.Policy.Beta.sum": { "value": 0.00020960000000000022, "min": 0.00020960000000000022, "max": 0.0048503, "count": 32 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1661170471", "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./trained-envs-executables/linux/Worm/Worm --run-id=Worm Training --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": "1.21.6", "end_time_seconds": "1661172498" }, "total": 2027.556556756, "count": 1, "self": 0.4789351560000341, "children": { "run_training.setup": { "total": 0.04303817300001356, "count": 1, "self": 0.04303817300001356 }, "TrainerController.start_learning": { "total": 2027.034583427, "count": 1, "self": 2.4489241670437423, "children": { "TrainerController._reset_env": { "total": 5.801588437999953, "count": 1, "self": 5.801588437999953 }, "TrainerController.advance": { "total": 2018.677996256957, "count": 101000, "self": 2.69152706696309, "children": { "env_step": { "total": 1000.9528573719622, "count": 101000, "self": 814.7030263138631, "children": { "SubprocessEnvManager._take_step": { "total": 184.6760236460405, "count": 101000, "self": 9.863698247066225, "children": { "TorchPolicy.evaluate": { "total": 174.81232539897428, "count": 101000, "self": 16.20775143298698, "children": { "TorchPolicy.sample_actions": { "total": 158.6045739659873, "count": 101000, "self": 158.6045739659873 } } } } }, "workers": { "total": 1.5738074120586134, "count": 101000, "self": 0.0, "children": { "worker_root": { "total": 2021.5959748140533, "count": 101000, "is_parallel": true, "self": 1333.755458955022, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0059169320000478365, "count": 1, "is_parallel": true, "self": 0.0003039900000203488, "children": { "_process_rank_one_or_two_observation": { "total": 0.005612942000027488, "count": 2, "is_parallel": true, "self": 0.005612942000027488 } } }, "UnityEnvironment.step": { "total": 0.02864007800002355, "count": 1, "is_parallel": true, "self": 0.00017858000006754082, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003481999999621621, "count": 1, "is_parallel": true, "self": 0.0003481999999621621 }, "communicator.exchange": { "total": 0.027626118000000588, "count": 1, "is_parallel": true, "self": 0.027626118000000588 }, "steps_from_proto": { "total": 0.0004871799999932591, "count": 1, "is_parallel": true, "self": 0.00018890000001192675, "children": { "_process_rank_one_or_two_observation": { "total": 0.00029827999998133237, "count": 2, "is_parallel": true, "self": 0.00029827999998133237 } } } } } } }, "UnityEnvironment.step": { "total": 687.8405158590313, "count": 100999, "is_parallel": true, "self": 15.610936331952189, "children": { "UnityEnvironment._generate_step_input": { "total": 19.956938699030445, "count": 100999, "is_parallel": true, "self": 19.956938699030445 }, "communicator.exchange": { "total": 610.6971288059959, "count": 100999, "is_parallel": true, "self": 610.6971288059959 }, "steps_from_proto": { "total": 41.57551202205258, "count": 100999, "is_parallel": true, "self": 16.53200554612772, "children": { "_process_rank_one_or_two_observation": { "total": 25.043506475924858, "count": 201998, "is_parallel": true, "self": 25.043506475924858 } } } } } } } } } } }, "trainer_advance": { "total": 1015.0336118180315, "count": 101000, "self": 3.420643004977478, "children": { "process_trajectory": { "total": 111.70502720305382, "count": 101000, "self": 111.47339327305355, "children": { "RLTrainer._checkpoint": { "total": 0.231633930000271, "count": 2, "self": 0.231633930000271 } } }, "_update_policy": { "total": 899.9079416100002, "count": 33, "self": 135.67550524200692, "children": { "TorchPPOOptimizer.update": { "total": 764.2324363679933, "count": 1386, "self": 764.2324363679933 } } } } } } }, "trainer_threads": { "total": 8.999995770864189e-07, "count": 1, "self": 8.999995770864189e-07 }, "TrainerController._save_models": { "total": 0.10607366499971249, "count": 1, "self": 0.004812789999505185, "children": { "RLTrainer._checkpoint": { "total": 0.1012608750002073, "count": 1, "self": 0.1012608750002073 } } } } } } }