{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7737569808959961, "min": 0.7693873643875122, "max": 2.8618276119232178, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7353.7861328125, "min": 7353.7861328125, "max": 29213.53515625, "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": 12.025435447692871, "min": 0.4061250686645508, "max": 12.025435447692871, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2344.9599609375, "min": 78.78826141357422, "max": 2430.31494140625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07066978417837982, "min": 0.06505466999164233, "max": 0.07298978196979757, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2826791367135193, "min": 0.2602440870558733, "max": 0.3580059741741256, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18326836926679985, "min": 0.10071811700175862, "max": 0.273265249004551, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7330734770671994, "min": 0.40287246800703447, "max": 1.3663262450227551, "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.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.Environment.CumulativeReward.mean": { "value": 23.65909090909091, "min": 3.159090909090909, "max": 23.672727272727272, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1041.0, "min": 139.0, "max": 1302.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.65909090909091, "min": 3.159090909090909, "max": 23.672727272727272, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1041.0, "min": 139.0, "max": 1302.0, "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": "1777144874", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "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": "1777145337" }, "total": 462.9261083839999, "count": 1, "self": 0.48330497499989633, "children": { "run_training.setup": { "total": 0.028517625000063163, "count": 1, "self": 0.028517625000063163 }, "TrainerController.start_learning": { "total": 462.41428578399996, "count": 1, "self": 0.3893171110023559, "children": { "TrainerController._reset_env": { "total": 4.062175799999977, "count": 1, "self": 4.062175799999977 }, "TrainerController.advance": { "total": 457.8845830219975, "count": 18192, "self": 0.41427822199091224, "children": { "env_step": { "total": 334.9686227770137, "count": 18192, "self": 260.86587374701196, "children": { "SubprocessEnvManager._take_step": { "total": 73.87662040498674, "count": 18192, "self": 1.307807045998402, "children": { "TorchPolicy.evaluate": { "total": 72.56881335898834, "count": 18192, "self": 72.56881335898834 } } }, "workers": { "total": 0.22612862501500786, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 460.4480022870025, "count": 18192, "is_parallel": true, "self": 231.3848557289881, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005410800000049676, "count": 1, "is_parallel": true, "self": 0.0032562020002160352, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021545979998336406, "count": 10, "is_parallel": true, "self": 0.0021545979998336406 } } }, "UnityEnvironment.step": { "total": 0.03822830599995086, "count": 1, "is_parallel": true, "self": 0.000579691000098137, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004055869999319839, "count": 1, "is_parallel": true, "self": 0.0004055869999319839 }, "communicator.exchange": { "total": 0.03534538199994586, "count": 1, "is_parallel": true, "self": 0.03534538199994586 }, "steps_from_proto": { "total": 0.001897645999974884, "count": 1, "is_parallel": true, "self": 0.00037012099994626624, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015275250000286178, "count": 10, "is_parallel": true, "self": 0.0015275250000286178 } } } } } } }, "UnityEnvironment.step": { "total": 229.0631465580144, "count": 18191, "is_parallel": true, "self": 10.70204534303673, "children": { "UnityEnvironment._generate_step_input": { "total": 5.737942605986518, "count": 18191, "is_parallel": true, "self": 5.737942605986518 }, "communicator.exchange": { "total": 174.42380015499145, "count": 18191, "is_parallel": true, "self": 174.42380015499145 }, "steps_from_proto": { "total": 38.19935845399971, "count": 18191, "is_parallel": true, "self": 6.7467207620496765, "children": { "_process_rank_one_or_two_observation": { "total": 31.45263769195003, "count": 181910, "is_parallel": true, "self": 31.45263769195003 } } } } } } } } } } }, "trainer_advance": { "total": 122.5016820229929, "count": 18192, "self": 0.47093066102854664, "children": { "process_trajectory": { "total": 27.158499681963917, "count": 18192, "self": 26.712706859963532, "children": { "RLTrainer._checkpoint": { "total": 0.44579282200038506, "count": 4, "self": 0.44579282200038506 } } }, "_update_policy": { "total": 94.87225168000043, "count": 90, "self": 38.38360591600156, "children": { "TorchPPOOptimizer.update": { "total": 56.488645763998875, "count": 4587, "self": 56.488645763998875 } } } } } } }, "trainer_threads": { "total": 9.060001957550412e-07, "count": 1, "self": 9.060001957550412e-07 }, "TrainerController._save_models": { "total": 0.07820894499991482, "count": 1, "self": 0.0006947540000510344, "children": { "RLTrainer._checkpoint": { "total": 0.07751419099986379, "count": 1, "self": 0.07751419099986379 } } } } } } }