{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.7892696857452393, "min": 1.7892696857452393, "max": 2.865532159805298, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 17103.62890625, "min": 17103.62890625, "max": 29535.0390625, "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": 11.066146850585938, "min": 0.3289164900779724, "max": 11.066146850585938, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2157.898681640625, "min": 63.80979919433594, "max": 2157.898681640625, "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": 0.10457271703275824, "min": 0.0936424283655514, "max": 0.10457271703275824, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.41829086813103294, "min": 0.3775792951316718, "max": 0.5175516889537092, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22665078662262828, "min": 0.11391797477785615, "max": 0.24596823822049535, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9066031464905131, "min": 0.4556718991114246, "max": 1.2298411911024767, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082009730600007e-05, "min": 8.082009730600007e-05, "max": 0.0029188200027060007, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00032328038922400026, "min": 0.00032328038922400026, "max": 0.013851600038279994, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269399999999997, "min": 0.10269399999999997, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077599999999986, "min": 0.41077599999999986, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0013567306000000006, "min": 0.0013567306000000006, "max": 0.04864727059999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0054269224000000026, "min": 0.0054269224000000026, "max": 0.23086382800000005, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 22.795454545454547, "min": 3.022727272727273, "max": 22.795454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1003.0, "min": 133.0, "max": 1238.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.795454545454547, "min": 3.022727272727273, "max": 22.795454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1003.0, "min": 133.0, "max": 1238.0, "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": "1724782095", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724782874" }, "total": 778.649982273, "count": 1, "self": 0.6459648139999672, "children": { "run_training.setup": { "total": 0.08062544300003083, "count": 1, "self": 0.08062544300003083 }, "TrainerController.start_learning": { "total": 777.923392016, "count": 1, "self": 1.1323788869995042, "children": { "TrainerController._reset_env": { "total": 3.56966762899998, "count": 1, "self": 3.56966762899998 }, "TrainerController.advance": { "total": 773.1269728820006, "count": 18201, "self": 0.5374086779960408, "children": { "env_step": { "total": 772.5895642040045, "count": 18201, "self": 606.9879311989886, "children": { "SubprocessEnvManager._take_step": { "total": 165.0820709000035, "count": 18201, "self": 3.5770158660047287, "children": { "TorchPolicy.evaluate": { "total": 161.50505503399876, "count": 18201, "self": 161.50505503399876 } } }, "workers": { "total": 0.5195621050124828, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 775.0494777240069, "count": 18201, "is_parallel": true, "self": 380.3983802810029, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003174059999992096, "count": 1, "is_parallel": true, "self": 0.000983630999826346, "children": { "_process_rank_one_or_two_observation": { "total": 0.00219042900016575, "count": 10, "is_parallel": true, "self": 0.00219042900016575 } } }, "UnityEnvironment.step": { "total": 0.09357919399997172, "count": 1, "is_parallel": true, "self": 0.0009770699999762655, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005572030000280392, "count": 1, "is_parallel": true, "self": 0.0005572030000280392 }, "communicator.exchange": { "total": 0.08918132399998058, "count": 1, "is_parallel": true, "self": 0.08918132399998058 }, "steps_from_proto": { "total": 0.0028635969999868394, "count": 1, "is_parallel": true, "self": 0.0006061420000378348, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022574549999490046, "count": 10, "is_parallel": true, "self": 0.0022574549999490046 } } } } } } }, "UnityEnvironment.step": { "total": 394.651097443004, "count": 18200, "is_parallel": true, "self": 19.04487494699771, "children": { "UnityEnvironment._generate_step_input": { "total": 9.041521468000838, "count": 18200, "is_parallel": true, "self": 9.041521468000838 }, "communicator.exchange": { "total": 312.3900486530039, "count": 18200, "is_parallel": true, "self": 312.3900486530039 }, "steps_from_proto": { "total": 54.174652375001585, "count": 18200, "is_parallel": true, "self": 11.129894361006734, "children": { "_process_rank_one_or_two_observation": { "total": 43.04475801399485, "count": 182000, "is_parallel": true, "self": 43.04475801399485 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00030822500002614106, "count": 1, "self": 0.00030822500002614106, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 764.2967663200193, "count": 892607, "is_parallel": true, "self": 23.268335844022886, "children": { "process_trajectory": { "total": 397.9369668499967, "count": 892607, "is_parallel": true, "self": 397.24411924799665, "children": { "RLTrainer._checkpoint": { "total": 0.6928476020000289, "count": 4, "is_parallel": true, "self": 0.6928476020000289 } } }, "_update_policy": { "total": 343.09146362599967, "count": 90, "is_parallel": true, "self": 80.04931251900297, "children": { "TorchPPOOptimizer.update": { "total": 263.0421511069967, "count": 9177, "is_parallel": true, "self": 263.0421511069967 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09406439299982594, "count": 1, "self": 0.0013414469997314882, "children": { "RLTrainer._checkpoint": { "total": 0.09272294600009445, "count": 1, "self": 0.09272294600009445 } } } } } } }