{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9549744129180908, "min": 0.9549744129180908, "max": 2.861483097076416, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9107.5908203125, "min": 9107.5908203125, "max": 29461.830078125, "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": 13.066909790039062, "min": 0.3629564046859741, "max": 13.066909790039062, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2548.04736328125, "min": 70.41354370117188, "max": 2664.22900390625, "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": 0.07109605015127683, "min": 0.06370553922686525, "max": 0.07665426918623887, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28438420060510733, "min": 0.25522192279630174, "max": 0.35705889050355016, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2041466610834879, "min": 0.1426084146255116, "max": 0.2821066823660159, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8165866443339516, "min": 0.5704336585020464, "max": 1.4105334118300794, "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": 25.75, "min": 3.977272727272727, "max": 25.927272727272726, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1133.0, "min": 175.0, "max": 1426.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.75, "min": 3.977272727272727, "max": 25.927272727272726, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1133.0, "min": 175.0, "max": 1426.0, "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": "1678689961", "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 /content/ml-agents/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": "1.23.5", "end_time_seconds": "1678690442" }, "total": 480.70779178299995, "count": 1, "self": 0.43622933299980104, "children": { "run_training.setup": { "total": 0.026326297999958115, "count": 1, "self": 0.026326297999958115 }, "TrainerController.start_learning": { "total": 480.2452361520002, "count": 1, "self": 0.5686660029909945, "children": { "TrainerController._reset_env": { "total": 4.944589041999961, "count": 1, "self": 4.944589041999961 }, "TrainerController.advance": { "total": 474.60498858200936, "count": 18204, "self": 0.29629830599355955, "children": { "env_step": { "total": 474.3086902760158, "count": 18204, "self": 339.52806587200007, "children": { "SubprocessEnvManager._take_step": { "total": 134.49961800600317, "count": 18204, "self": 1.580161860011458, "children": { "TorchPolicy.evaluate": { "total": 132.91945614599172, "count": 18204, "self": 29.708426574962232, "children": { "TorchPolicy.sample_actions": { "total": 103.21102957102948, "count": 18204, "self": 103.21102957102948 } } } } }, "workers": { "total": 0.28100639801255056, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 478.2532824419866, "count": 18204, "is_parallel": true, "self": 223.24850261199163, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022004219999871566, "count": 1, "is_parallel": true, "self": 0.0007708449993515387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014295770006356179, "count": 10, "is_parallel": true, "self": 0.0014295770006356179 } } }, "UnityEnvironment.step": { "total": 0.10599785599993083, "count": 1, "is_parallel": true, "self": 0.0007139760000427486, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004383329999200214, "count": 1, "is_parallel": true, "self": 0.0004383329999200214 }, "communicator.exchange": { "total": 0.10133724899992558, "count": 1, "is_parallel": true, "self": 0.10133724899992558 }, "steps_from_proto": { "total": 0.003508298000042487, "count": 1, "is_parallel": true, "self": 0.0004888209998625825, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030194770001799043, "count": 10, "is_parallel": true, "self": 0.0030194770001799043 } } } } } } }, "UnityEnvironment.step": { "total": 255.00477982999496, "count": 18203, "is_parallel": true, "self": 10.031287674020177, "children": { "UnityEnvironment._generate_step_input": { "total": 5.621894564987542, "count": 18203, "is_parallel": true, "self": 5.621894564987542 }, "communicator.exchange": { "total": 207.26217878400644, "count": 18203, "is_parallel": true, "self": 207.26217878400644 }, "steps_from_proto": { "total": 32.0894188069808, "count": 18203, "is_parallel": true, "self": 7.190594462031868, "children": { "_process_rank_one_or_two_observation": { "total": 24.898824344948935, "count": 182030, "is_parallel": true, "self": 24.898824344948935 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013382099996306351, "count": 1, "self": 0.00013382099996306351, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 470.6791769880142, "count": 448612, "is_parallel": true, "self": 11.857541027128491, "children": { "process_trajectory": { "total": 272.7526272088867, "count": 448612, "is_parallel": true, "self": 271.55548101188674, "children": { "RLTrainer._checkpoint": { "total": 1.1971461969999382, "count": 4, "is_parallel": true, "self": 1.1971461969999382 } } }, "_update_policy": { "total": 186.06900875199904, "count": 90, "is_parallel": true, "self": 66.88458531099036, "children": { "TorchPPOOptimizer.update": { "total": 119.18442344100868, "count": 4587, "is_parallel": true, "self": 119.18442344100868 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12685870399991472, "count": 1, "self": 0.0008838239998567587, "children": { "RLTrainer._checkpoint": { "total": 0.12597488000005796, "count": 1, "self": 0.12597488000005796 } } } } } } }