{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2601354122161865, "min": 1.2601354122161865, "max": 2.872541666030884, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12059.49609375, "min": 12059.49609375, "max": 29512.494140625, "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": 12.060037612915039, "min": 0.412763774394989, "max": 12.060037612915039, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2351.707275390625, "min": 80.076171875, "max": 2437.3544921875, "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": 0.06942194825487427, "min": 0.06440966163063422, "max": 0.07798915376088367, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2776877930194971, "min": 0.2576386465225369, "max": 0.38994576880441834, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2212587353207317, "min": 0.11046438008391608, "max": 0.2880520590964485, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8850349412829268, "min": 0.44185752033566433, "max": 1.4402602954822425, "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": 24.681818181818183, "min": 3.022727272727273, "max": 24.681818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1086.0, "min": 133.0, "max": 1298.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.681818181818183, "min": 3.022727272727273, "max": 24.681818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1086.0, "min": 133.0, "max": 1298.0, "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": "1675923020", "python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]", "command_line_arguments": "/home/jackmin/miniconda3/envs/unit4/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1675923380" }, "total": 360.89430714200716, "count": 1, "self": 0.27066009101690724, "children": { "run_training.setup": { "total": 0.027968355978373438, "count": 1, "self": 0.027968355978373438 }, "TrainerController.start_learning": { "total": 360.5956786950119, "count": 1, "self": 0.39902724110288545, "children": { "TrainerController._reset_env": { "total": 3.8192723690299317, "count": 1, "self": 3.8192723690299317 }, "TrainerController.advance": { "total": 356.275436320866, "count": 18208, "self": 0.1969151677330956, "children": { "env_step": { "total": 356.0785211531329, "count": 18208, "self": 276.25378280034056, "children": { "SubprocessEnvManager._take_step": { "total": 79.61595326761017, "count": 18208, "self": 1.2173556858324446, "children": { "TorchPolicy.evaluate": { "total": 78.39859758177772, "count": 18208, "self": 78.39859758177772 } } }, "workers": { "total": 0.20878508518217131, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 359.87866561021656, "count": 18208, "is_parallel": true, "self": 163.6055859705084, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024752579629421234, "count": 1, "is_parallel": true, "self": 0.0007688608020544052, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017063971608877182, "count": 10, "is_parallel": true, "self": 0.0017063971608877182 } } }, "UnityEnvironment.step": { "total": 0.027589798963163048, "count": 1, "is_parallel": true, "self": 0.0006086789653636515, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039775698678568006, "count": 1, "is_parallel": true, "self": 0.00039775698678568006 }, "communicator.exchange": { "total": 0.024827146029565483, "count": 1, "is_parallel": true, "self": 0.024827146029565483 }, "steps_from_proto": { "total": 0.0017562169814482331, "count": 1, "is_parallel": true, "self": 0.00033735594479367137, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014188610366545618, "count": 10, "is_parallel": true, "self": 0.0014188610366545618 } } } } } } }, "UnityEnvironment.step": { "total": 196.27307963970816, "count": 18207, "is_parallel": true, "self": 10.10665042605251, "children": { "UnityEnvironment._generate_step_input": { "total": 5.528143003000878, "count": 18207, "is_parallel": true, "self": 5.528143003000878 }, "communicator.exchange": { "total": 151.83287960395683, "count": 18207, "is_parallel": true, "self": 151.83287960395683 }, "steps_from_proto": { "total": 28.805406606697943, "count": 18207, "is_parallel": true, "self": 5.370519056217745, "children": { "_process_rank_one_or_two_observation": { "total": 23.434887550480198, "count": 182070, "is_parallel": true, "self": 23.434887550480198 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014602200826629996, "count": 1, "self": 0.00014602200826629996, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 355.61471569689456, "count": 177435, "is_parallel": true, "self": 2.3999547627172433, "children": { "process_trajectory": { "total": 200.42583679308882, "count": 177435, "is_parallel": true, "self": 199.57177530403715, "children": { "RLTrainer._checkpoint": { "total": 0.8540614890516736, "count": 4, "is_parallel": true, "self": 0.8540614890516736 } } }, "_update_policy": { "total": 152.7889241410885, "count": 90, "is_parallel": true, "self": 35.93603744456777, "children": { "TorchPPOOptimizer.update": { "total": 116.85288669652073, "count": 4587, "is_parallel": true, "self": 116.85288669652073 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10179674200480804, "count": 1, "self": 0.0005566280451603234, "children": { "RLTrainer._checkpoint": { "total": 0.10124011395964772, "count": 1, "self": 0.10124011395964772 } } } } } } }