{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.524087905883789, "min": 1.524087905883789, "max": 2.890340805053711, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 14568.755859375, "min": 14568.755859375, "max": 29631.7734375, "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": 8.589315414428711, "min": 0.027471229434013367, "max": 8.589315414428711, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1674.91650390625, "min": 5.329418659210205, "max": 1681.61962890625, "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.Environment.CumulativeReward.mean": { "value": 21.704545454545453, "min": 2.6363636363636362, "max": 22.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 955.0, "min": 116.0, "max": 1230.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 21.704545454545453, "min": 2.6363636363636362, "max": 22.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 955.0, "min": 116.0, "max": 1230.0, "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 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.03813731559494045, "min": 0.030352596685144163, "max": 0.03813731559494045, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.03813731559494045, "min": 0.030352596685144163, "max": 0.03813731559494045, "count": 19 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.261536289538656, "min": 0.07737695226879944, "max": 0.33659222083432333, "count": 19 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.261536289538656, "min": 0.07737695226879944, "max": 0.33659222083432333, "count": 19 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.488097503999998e-06, "min": 7.488097503999998e-06, "max": 0.00028468800510399997, "count": 19 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 7.488097503999998e-06, "min": 7.488097503999998e-06, "max": 0.00028468800510399997, "count": 19 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10499199999999999, "min": 0.10499199999999999, "max": 0.28979199999999994, "count": 19 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10499199999999999, "min": 0.10499199999999999, "max": 0.28979199999999994, "count": 19 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00013455039999999988, "min": 0.00013455039999999988, "max": 0.0047453104, "count": 19 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00013455039999999988, "min": 0.00013455039999999988, "max": 0.0047453104, "count": 19 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692546882", "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 --force", "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": "1692547414" }, "total": 531.493570528, "count": 1, "self": 0.438592632000109, "children": { "run_training.setup": { "total": 0.050082269000085944, "count": 1, "self": 0.050082269000085944 }, "TrainerController.start_learning": { "total": 531.0048956269998, "count": 1, "self": 0.5461930540013782, "children": { "TrainerController._reset_env": { "total": 4.4186103289998755, "count": 1, "self": 4.4186103289998755 }, "TrainerController.advance": { "total": 525.8932921079986, "count": 18202, "self": 0.2556655550188225, "children": { "env_step": { "total": 525.6376265529798, "count": 18202, "self": 405.4591730799416, "children": { "SubprocessEnvManager._take_step": { "total": 119.91368708700747, "count": 18202, "self": 1.9687249190587863, "children": { "TorchPolicy.evaluate": { "total": 117.94496216794869, "count": 18202, "self": 117.94496216794869 } } }, "workers": { "total": 0.2647663860307148, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 529.6026522519887, "count": 18202, "is_parallel": true, "self": 290.3153083829852, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018283710001014697, "count": 1, "is_parallel": true, "self": 0.0004956860011589015, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013326849989425682, "count": 10, "is_parallel": true, "self": 0.0013326849989425682 } } }, "UnityEnvironment.step": { "total": 0.06508506799991665, "count": 1, "is_parallel": true, "self": 0.0006614669996451994, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004135310000492609, "count": 1, "is_parallel": true, "self": 0.0004135310000492609 }, "communicator.exchange": { "total": 0.061839138000323146, "count": 1, "is_parallel": true, "self": 0.061839138000323146 }, "steps_from_proto": { "total": 0.0021709319998990395, "count": 1, "is_parallel": true, "self": 0.0005372180003178073, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016337139995812322, "count": 10, "is_parallel": true, "self": 0.0016337139995812322 } } } } } } }, "UnityEnvironment.step": { "total": 239.2873438690035, "count": 18201, "is_parallel": true, "self": 10.342141128946878, "children": { "UnityEnvironment._generate_step_input": { "total": 5.226137717036181, "count": 18201, "is_parallel": true, "self": 5.226137717036181 }, "communicator.exchange": { "total": 188.4299399129991, "count": 18201, "is_parallel": true, "self": 188.4299399129991 }, "steps_from_proto": { "total": 35.28912511002136, "count": 18201, "is_parallel": true, "self": 6.320004223180604, "children": { "_process_rank_one_or_two_observation": { "total": 28.969120886840756, "count": 182010, "is_parallel": true, "self": 28.969120886840756 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017537399980938062, "count": 1, "self": 0.00017537399980938062, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 520.6744152131068, "count": 594430, "is_parallel": true, "self": 13.519625416097824, "children": { "process_trajectory": { "total": 327.58573930000966, "count": 594430, "is_parallel": true, "self": 326.30826315300965, "children": { "RLTrainer._checkpoint": { "total": 1.2774761470000158, "count": 4, "is_parallel": true, "self": 1.2774761470000158 } } }, "_update_policy": { "total": 179.56905049699935, "count": 19, "is_parallel": true, "self": 129.0545505799896, "children": { "TorchPPOOptimizer.update": { "total": 50.51449991700974, "count": 2611, "is_parallel": true, "self": 50.51449991700974 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14662476200010133, "count": 1, "self": 0.0010891460001403175, "children": { "RLTrainer._checkpoint": { "total": 0.145535615999961, "count": 1, "self": 0.145535615999961 } } } } } } }