{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.053879976272583, "min": 1.053879976272583, "max": 2.8711061477661133, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10074.0390625, "min": 10074.0390625, "max": 29434.580078125, "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": 12.69166374206543, "min": 0.33791059255599976, "max": 12.69166374206543, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2474.87451171875, "min": 65.55465698242188, "max": 2578.519775390625, "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": 0.06605779284052238, "min": 0.06459511697107433, "max": 0.07528448936200756, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2642311713620895, "min": 0.2591387862679161, "max": 0.3764224468100378, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20172349655745075, "min": 0.12096190185276973, "max": 0.27528326038052053, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.806893986229803, "min": 0.4838476074110789, "max": 1.3073280143971535, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.204545454545453, "min": 3.4318181818181817, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1109.0, "min": 151.0, "max": 1364.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.204545454545453, "min": 3.4318181818181817, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1109.0, "min": 151.0, "max": 1364.0, "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": "1728973021", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/Snowballtarget.yaml --env=/content/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget4 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728973424" }, "total": 403.589667059, "count": 1, "self": 0.424637258999951, "children": { "run_training.setup": { "total": 0.06121889300004568, "count": 1, "self": 0.06121889300004568 }, "TrainerController.start_learning": { "total": 403.103810907, "count": 1, "self": 0.5137059849979551, "children": { "TrainerController._reset_env": { "total": 1.3606555989999833, "count": 1, "self": 1.3606555989999833 }, "TrainerController.advance": { "total": 401.16178144600224, "count": 18203, "self": 0.24640943600945775, "children": { "env_step": { "total": 400.9153720099928, "count": 18203, "self": 310.0633719099802, "children": { "SubprocessEnvManager._take_step": { "total": 90.5868037519997, "count": 18203, "self": 1.3365379410014384, "children": { "TorchPolicy.evaluate": { "total": 89.25026581099826, "count": 18203, "self": 89.25026581099826 } } }, "workers": { "total": 0.2651963480128643, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 402.04996915298636, "count": 18203, "is_parallel": true, "self": 191.76013326399482, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021873140000252533, "count": 1, "is_parallel": true, "self": 0.0006438970001454436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015434169998798097, "count": 10, "is_parallel": true, "self": 0.0015434169998798097 } } }, "UnityEnvironment.step": { "total": 0.0345052540000097, "count": 1, "is_parallel": true, "self": 0.0007039700001314486, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037114099995960714, "count": 1, "is_parallel": true, "self": 0.00037114099995960714 }, "communicator.exchange": { "total": 0.031510865999962334, "count": 1, "is_parallel": true, "self": 0.031510865999962334 }, "steps_from_proto": { "total": 0.0019192769999563097, "count": 1, "is_parallel": true, "self": 0.0003672700001970952, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015520069997592145, "count": 10, "is_parallel": true, "self": 0.0015520069997592145 } } } } } } }, "UnityEnvironment.step": { "total": 210.28983588899155, "count": 18202, "is_parallel": true, "self": 9.681426020008871, "children": { "UnityEnvironment._generate_step_input": { "total": 5.104762903994583, "count": 18202, "is_parallel": true, "self": 5.104762903994583 }, "communicator.exchange": { "total": 164.4510478799948, "count": 18202, "is_parallel": true, "self": 164.4510478799948 }, "steps_from_proto": { "total": 31.05259908499329, "count": 18202, "is_parallel": true, "self": 5.623571209972965, "children": { "_process_rank_one_or_two_observation": { "total": 25.429027875020324, "count": 182020, "is_parallel": true, "self": 25.429027875020324 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.982699998545286e-05, "count": 1, "self": 9.982699998545286e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 396.9005676618623, "count": 551130, "is_parallel": true, "self": 10.952654450946511, "children": { "process_trajectory": { "total": 208.82457134091408, "count": 551130, "is_parallel": true, "self": 208.26498902691435, "children": { "RLTrainer._checkpoint": { "total": 0.5595823139997265, "count": 4, "is_parallel": true, "self": 0.5595823139997265 } } }, "_update_policy": { "total": 177.1233418700017, "count": 90, "is_parallel": true, "self": 54.925099440000054, "children": { "TorchPPOOptimizer.update": { "total": 122.19824243000164, "count": 4587, "is_parallel": true, "self": 122.19824243000164 } } } } } } } } }, "TrainerController._save_models": { "total": 0.06756804999986343, "count": 1, "self": 0.0009830899998632958, "children": { "RLTrainer._checkpoint": { "total": 0.06658496000000014, "count": 1, "self": 0.06658496000000014 } } } } } } }