{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.840329885482788, "min": 2.840329885482788, "max": 2.871807336807251, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 29119.0625, "min": 29119.0625, "max": 29536.5390625, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.18097722530365, "min": 0.373162180185318, "max": 1.18097722530365, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 242.10032653808594, "min": 72.39346313476562, "max": 242.10032653808594, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07142591745588088, "min": 0.0649059384972954, "max": 0.07142591745588088, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3571295872794044, "min": 0.2596237539891816, "max": 0.3571295872794044, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16272486994663876, "min": 0.10600450051510157, "max": 0.16272486994663876, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8136243497331938, "min": 0.4240180020604063, "max": 0.8136243497331938, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032007656e-05, "min": 7.032007656e-05, "max": 0.00021882002706000002, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003516003828, "min": 0.0003516003828, "max": 0.0008752801082400001, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12344000000000002, "min": 0.12344000000000002, "max": 0.17294, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6172000000000001, "min": 0.6172000000000001, "max": 0.69176, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011796560000000003, "min": 0.0011796560000000003, "max": 0.003649706, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005898280000000001, "min": 0.005898280000000001, "max": 0.014598824, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 4.909090909090909, "min": 3.1818181818181817, "max": 4.909090909090909, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 270.0, "min": 140.0, "max": 270.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 4.909090909090909, "min": 3.1818181818181817, "max": 4.909090909090909, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 270.0, "min": 140.0, "max": 270.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680968301", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1680968353" }, "total": 51.606883371000094, "count": 1, "self": 0.3796194710000691, "children": { "run_training.setup": { "total": 0.11134202100004131, "count": 1, "self": 0.11134202100004131 }, "TrainerController.start_learning": { "total": 51.115921878999984, "count": 1, "self": 0.08858157000372557, "children": { "TrainerController._reset_env": { "total": 3.8181750890000785, "count": 1, "self": 3.8181750890000785 }, "TrainerController.advance": { "total": 47.05203365499631, "count": 1868, "self": 0.026734972996905526, "children": { "env_step": { "total": 47.0252986819994, "count": 1868, "self": 34.94318560199633, "children": { "SubprocessEnvManager._take_step": { "total": 12.054540875001635, "count": 1868, "self": 0.1569728829987298, "children": { "TorchPolicy.evaluate": { "total": 11.897567992002905, "count": 1868, "self": 11.897567992002905 } } }, "workers": { "total": 0.02757220500143376, "count": 1868, "self": 0.0, "children": { "worker_root": { "total": 50.888737218997676, "count": 1868, "is_parallel": true, "self": 25.78703435099669, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006216042999994897, "count": 1, "is_parallel": true, "self": 0.004860836999796447, "children": { "_process_rank_one_or_two_observation": { "total": 0.00135520600019845, "count": 10, "is_parallel": true, "self": 0.00135520600019845 } } }, "UnityEnvironment.step": { "total": 0.036192206999999144, "count": 1, "is_parallel": true, "self": 0.0005932459999939965, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038742300000649266, "count": 1, "is_parallel": true, "self": 0.00038742300000649266 }, "communicator.exchange": { "total": 0.03322854200007441, "count": 1, "is_parallel": true, "self": 0.03322854200007441 }, "steps_from_proto": { "total": 0.001982995999924242, "count": 1, "is_parallel": true, "self": 0.00040740199995070725, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015755939999735347, "count": 10, "is_parallel": true, "self": 0.0015755939999735347 } } } } } } }, "UnityEnvironment.step": { "total": 25.101702868000984, "count": 1867, "is_parallel": true, "self": 1.048601352998162, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5934415449994503, "count": 1867, "is_parallel": true, "self": 0.5934415449994503 }, "communicator.exchange": { "total": 20.040120929002114, "count": 1867, "is_parallel": true, "self": 20.040120929002114 }, "steps_from_proto": { "total": 3.419539041001258, "count": 1867, "is_parallel": true, "self": 0.6577940559980107, "children": { "_process_rank_one_or_two_observation": { "total": 2.761744985003247, "count": 18670, "is_parallel": true, "self": 2.761744985003247 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002760679999482818, "count": 1, "self": 0.0002760679999482818, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 46.73906956798123, "count": 39356, "is_parallel": true, "self": 0.9880046809939813, "children": { "process_trajectory": { "total": 26.063941266986944, "count": 39356, "is_parallel": true, "self": 26.063941266986944 }, "_update_policy": { "total": 19.687123620000307, "count": 9, "is_parallel": true, "self": 7.725112626999476, "children": { "TorchPPOOptimizer.update": { "total": 11.962010993000831, "count": 456, "is_parallel": true, "self": 11.962010993000831 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15685549699992407, "count": 1, "self": 0.0008685149999791975, "children": { "RLTrainer._checkpoint": { "total": 0.15598698199994487, "count": 1, "self": 0.15598698199994487 } } } } } } }