{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5291388034820557, "min": 0.5173834562301636, "max": 2.8587822914123535, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5413.08984375, "min": 4999.05712890625, "max": 29245.34375, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.239165306091309, "min": 0.3915049433708191, "max": 14.386966705322266, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2919.02880859375, "min": 75.95195770263672, "max": 2949.328125, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06509208678925302, "min": 0.05793846801337649, "max": 0.07891193099431784, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.32546043394626506, "min": 0.23175387205350595, "max": 0.3766518468328286, "count": 200 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15311466061017093, "min": 0.10854222133125671, "max": 0.2772454929848512, "count": 200 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7655733030508546, "min": 0.43416888532502684, "max": 1.3351598829030993, "count": 200 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032997656000039e-07, "min": 7.032997656000039e-07, "max": 0.00029918820027059994, "count": 200 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.5164988280000196e-06, "min": 3.5164988280000196e-06, "max": 0.0014885160038279998, "count": 200 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10023440000000002, "min": 0.10023440000000002, "max": 0.1997294, "count": 200 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5011720000000001, "min": 0.4029176, "max": 0.996172, "count": 200 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.1696560000000067e-05, "min": 2.1696560000000067e-05, "max": 0.004986497059999999, "count": 200 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00010848280000000034, "min": 0.00010848280000000034, "max": 0.024808982800000004, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.163636363636364, "min": 3.3863636363636362, "max": 28.477272727272727, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1549.0, "min": 149.0, "max": 1561.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.163636363636364, "min": 3.3863636363636362, "max": 28.477272727272727, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1549.0, "min": 149.0, "max": 1561.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1720130833", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720135482" }, "total": 4649.509552075001, "count": 1, "self": 0.48859560799974133, "children": { "run_training.setup": { "total": 0.05359070500071539, "count": 1, "self": 0.05359070500071539 }, "TrainerController.start_learning": { "total": 4648.967365762001, "count": 1, "self": 5.910175899049136, "children": { "TrainerController._reset_env": { "total": 2.937081534999379, "count": 1, "self": 2.937081534999379 }, "TrainerController.advance": { "total": 4640.029829719953, "count": 181872, "self": 2.9316713241478283, "children": { "env_step": { "total": 4637.0981583958055, "count": 181872, "self": 3022.50998150295, "children": { "SubprocessEnvManager._take_step": { "total": 1611.6955746918266, "count": 181872, "self": 15.139883063241541, "children": { "TorchPolicy.evaluate": { "total": 1596.555691628585, "count": 181872, "self": 1596.555691628585 } } }, "workers": { "total": 2.892602201029149, "count": 181872, "self": 0.0, "children": { "worker_root": { "total": 4636.800737390936, "count": 181872, "is_parallel": true, "self": 2318.011387791349, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030143000003590714, "count": 1, "is_parallel": true, "self": 0.0007683900012125378, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022459099991465337, "count": 10, "is_parallel": true, "self": 0.0022459099991465337 } } }, "UnityEnvironment.step": { "total": 0.07776201500018942, "count": 1, "is_parallel": true, "self": 0.0007039259999146452, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000420372999542451, "count": 1, "is_parallel": true, "self": 0.000420372999542451 }, "communicator.exchange": { "total": 0.07455213899993396, "count": 1, "is_parallel": true, "self": 0.07455213899993396 }, "steps_from_proto": { "total": 0.0020855770007983665, "count": 1, "is_parallel": true, "self": 0.0004085379996467964, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016770390011515701, "count": 10, "is_parallel": true, "self": 0.0016770390011515701 } } } } } } }, "UnityEnvironment.step": { "total": 2318.789349599587, "count": 181871, "is_parallel": true, "self": 103.76306407735319, "children": { "UnityEnvironment._generate_step_input": { "total": 55.42352665841645, "count": 181871, "is_parallel": true, "self": 55.42352665841645 }, "communicator.exchange": { "total": 1806.3840215860182, "count": 181871, "is_parallel": true, "self": 1806.3840215860182 }, "steps_from_proto": { "total": 353.21873727779894, "count": 181871, "is_parallel": true, "self": 66.42432226970959, "children": { "_process_rank_one_or_two_observation": { "total": 286.79441500808935, "count": 1818710, "is_parallel": true, "self": 286.79441500808935 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00028783099878637586, "count": 1, "self": 0.00028783099878637586, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 4582.17035785442, "count": 6804312, "is_parallel": true, "self": 154.48491806491893, "children": { "process_trajectory": { "total": 2526.759622636476, "count": 6804312, "is_parallel": true, "self": 2518.2699130204737, "children": { "RLTrainer._checkpoint": { "total": 8.489709616002074, "count": 40, "is_parallel": true, "self": 8.489709616002074 } } }, "_update_policy": { "total": 1900.9258171530255, "count": 909, "is_parallel": true, "self": 596.7985820900067, "children": { "TorchPPOOptimizer.update": { "total": 1304.1272350630188, "count": 46341, "is_parallel": true, "self": 1304.1272350630188 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08999077699991176, "count": 1, "self": 0.0013316320000740234, "children": { "RLTrainer._checkpoint": { "total": 0.08865914499983774, "count": 1, "self": 0.08865914499983774 } } } } } } }