{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9232632517814636, "min": 0.9232632517814636, "max": 2.8903205394744873, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9526.23046875, "min": 6136.150390625, "max": 27763.0234375, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199976.0, "min": 9984.0, "max": 199976.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199976.0, "min": 9984.0, "max": 199976.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.52334976196289, "min": 0.04826056957244873, "max": 12.52334976196289, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2567.28662109375, "min": 1.1582536697387695, "max": 2567.28662109375, "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.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06464404309232372, "min": 0.06402833573277651, "max": 0.07461803034290343, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3232202154616186, "min": 0.25611334293110605, "max": 0.3674637621993943, "count": 19 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20672569923541126, "min": 0.12773027302076417, "max": 0.2861822873353958, "count": 19 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0336284961770563, "min": 0.6386513651038209, "max": 1.430911436676979, "count": 19 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.96009768e-06, "min": 6.96009768e-06, "max": 0.00027756000748, "count": 19 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.48004884e-05, "min": 3.48004884e-05, "max": 0.0013878000374, "count": 19 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10232, "min": 0.10232, "max": 0.19251999999999997, "count": 19 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5115999999999999, "min": 0.4290800000000001, "max": 0.9625999999999999, "count": 19 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.000125768, "min": 0.000125768, "max": 0.004626748000000001, "count": 19 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00062884, "min": 0.00062884, "max": 0.023133740000000003, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.0, "min": 3.6363636363636362, "max": 25.0, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1375.0, "min": 200.0, "max": 1375.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.6363636363636362, "max": 25.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1375.0, "min": 200.0, "max": 1375.0, "count": 19 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1784478087", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/shamik/anaconda3/envs/rl-env-py310/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1784478244" }, "total": 156.51600448099998, "count": 1, "self": 0.16676497899970855, "children": { "run_training.setup": { "total": 0.01253139199980069, "count": 1, "self": 0.01253139199980069 }, "TrainerController.start_learning": { "total": 156.33670811000047, "count": 1, "self": 0.26522381715403753, "children": { "TrainerController._reset_env": { "total": 1.2688414640033443, "count": 1, "self": 1.2688414640033443 }, "TrainerController.advance": { "total": 154.76168821884494, "count": 17474, "self": 0.11390320175632951, "children": { "env_step": { "total": 154.6477850170886, "count": 17474, "self": 101.56403748774028, "children": { "SubprocessEnvManager._take_step": { "total": 52.95641476590754, "count": 17474, "self": 0.6337312098221446, "children": { "TorchPolicy.evaluate": { "total": 52.322683556085394, "count": 17474, "self": 52.322683556085394 } } }, "workers": { "total": 0.1273327634407906, "count": 17474, "self": 0.0, "children": { "worker_root": { "total": 156.04375941084072, "count": 17474, "is_parallel": true, "self": 81.45517131637826, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012604310031747445, "count": 1, "is_parallel": true, "self": 0.0003426160074013751, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009178149957733694, "count": 10, "is_parallel": true, "self": 0.0009178149957733694 } } }, "UnityEnvironment.step": { "total": 0.012819602001400199, "count": 1, "is_parallel": true, "self": 0.00023316800070460886, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00015630300185875967, "count": 1, "is_parallel": true, "self": 0.00015630300185875967 }, "communicator.exchange": { "total": 0.011519275001774076, "count": 1, "is_parallel": true, "self": 0.011519275001774076 }, "steps_from_proto": { "total": 0.0009108559970627539, "count": 1, "is_parallel": true, "self": 0.00020338399554020725, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007074720015225466, "count": 10, "is_parallel": true, "self": 0.0007074720015225466 } } } } } } }, "UnityEnvironment.step": { "total": 74.58858809446247, "count": 17473, "is_parallel": true, "self": 3.2417108550071134, "children": { "UnityEnvironment._generate_step_input": { "total": 1.6185265582935244, "count": 17473, "is_parallel": true, "self": 1.6185265582935244 }, "communicator.exchange": { "total": 60.54157073416718, "count": 17473, "is_parallel": true, "self": 60.54157073416718 }, "steps_from_proto": { "total": 9.186779946994648, "count": 17473, "is_parallel": true, "self": 1.8350566700937634, "children": { "_process_rank_one_or_two_observation": { "total": 7.351723276900884, "count": 174730, "is_parallel": true, "self": 7.351723276900884 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013597200086223893, "count": 1, "self": 0.00013597200086223893, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 154.52339641787694, "count": 166930, "is_parallel": true, "self": 1.196502853414131, "children": { "process_trajectory": { "total": 86.64063019246532, "count": 166930, "is_parallel": true, "self": 86.30622246046914, "children": { "RLTrainer._checkpoint": { "total": 0.3344077319961798, "count": 4, "is_parallel": true, "self": 0.3344077319961798 } } }, "_update_policy": { "total": 66.68626337199748, "count": 87, "is_parallel": true, "self": 14.914750962019752, "children": { "TorchPPOOptimizer.update": { "total": 51.77151240997773, "count": 4434, "is_parallel": true, "self": 51.77151240997773 } } } } } } } } }, "TrainerController._save_models": { "total": 0.04081863799729035, "count": 1, "self": 0.00046686999485245906, "children": { "RLTrainer._checkpoint": { "total": 0.04035176800243789, "count": 1, "self": 0.04035176800243789 } } } } } } }