{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.87007075548172, "min": 0.8571820855140686, "max": 2.665627956390381, "count": 19 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8269.15234375, "min": 8269.15234375, "max": 23946.328125, "count": 19 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 19 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 19992.0, "max": 199984.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.028005599975586, "min": 1.848665475845337, "max": 13.028005599975586, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2540.461181640625, "min": 249.56983947753906, "max": 2646.088623046875, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07174146862006656, "min": 0.06283611220495752, "max": 0.07404320597547043, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2869658744802662, "min": 0.20686593932061093, "max": 0.36268202800263183, "count": 19 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2055351081139901, "min": 0.1978417685803245, "max": 0.2898271525753479, "count": 19 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8221404324559604, "min": 0.7168980026617646, "max": 1.3873297951969448, "count": 19 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000273732008756, "count": 19 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00123666008778, "count": 19 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.191244, "count": 19 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.91222, "count": 19 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0045630756, "count": 19 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.020619778000000002, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 6567.0, "max": 10945.0, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.40909090909091, "min": 7.424242424242424, "max": 25.795454545454547, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 245.0, "max": 1418.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 7.424242424242424, "max": 25.795454545454547, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 245.0, "max": 1418.0, "count": 19 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1784330101", "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 --resume", "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": "1784330564" }, "total": 463.261596154, "count": 1, "self": 0.43388247700022475, "children": { "run_training.setup": { "total": 0.025127798000085022, "count": 1, "self": 0.025127798000085022 }, "TrainerController.start_learning": { "total": 462.8025858789997, "count": 1, "self": 0.43135089100542245, "children": { "TrainerController._reset_env": { "total": 2.0722338129999116, "count": 1, "self": 2.0722338129999116 }, "TrainerController.advance": { "total": 460.2165094319944, "count": 16992, "self": 0.43877945595932033, "children": { "env_step": { "total": 342.1979538540031, "count": 16992, "self": 267.7088001920565, "children": { "SubprocessEnvManager._take_step": { "total": 74.21992059490958, "count": 16992, "self": 1.3496146918960221, "children": { "TorchPolicy.evaluate": { "total": 72.87030590301356, "count": 16992, "self": 72.87030590301356 } } }, "workers": { "total": 0.2692330670370211, "count": 16992, "self": 0.0, "children": { "worker_root": { "total": 460.8201482589843, "count": 16992, "is_parallel": true, "self": 226.67615600897443, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024085670002023107, "count": 1, "is_parallel": true, "self": 0.0007847170004424697, "children": { "_process_rank_one_or_two_observation": { "total": 0.001623849999759841, "count": 10, "is_parallel": true, "self": 0.001623849999759841 } } }, "UnityEnvironment.step": { "total": 0.041948340000089956, "count": 1, "is_parallel": true, "self": 0.0006335369998851093, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004519519998211763, "count": 1, "is_parallel": true, "self": 0.0004519519998211763 }, "communicator.exchange": { "total": 0.03883406900013142, "count": 1, "is_parallel": true, "self": 0.03883406900013142 }, "steps_from_proto": { "total": 0.0020287820002522494, "count": 1, "is_parallel": true, "self": 0.00037473500105988933, "children": { "_process_rank_one_or_two_observation": { "total": 0.00165404699919236, "count": 10, "is_parallel": true, "self": 0.00165404699919236 } } } } } } }, "UnityEnvironment.step": { "total": 234.1439922500099, "count": 16991, "is_parallel": true, "self": 10.35009592603592, "children": { "UnityEnvironment._generate_step_input": { "total": 5.613845507002679, "count": 16991, "is_parallel": true, "self": 5.613845507002679 }, "communicator.exchange": { "total": 180.1272439339955, "count": 16991, "is_parallel": true, "self": 180.1272439339955 }, "steps_from_proto": { "total": 38.0528068829758, "count": 16991, "is_parallel": true, "self": 6.839617024669678, "children": { "_process_rank_one_or_two_observation": { "total": 31.213189858306123, "count": 169910, "is_parallel": true, "self": 31.213189858306123 } } } } } } } } } } }, "trainer_advance": { "total": 117.57977612203194, "count": 16992, "self": 0.5312661341417879, "children": { "process_trajectory": { "total": 24.465700950893734, "count": 16992, "self": 24.03762795489456, "children": { "RLTrainer._checkpoint": { "total": 0.42807299599917314, "count": 4, "self": 0.42807299599917314 } } }, "_update_policy": { "total": 92.58280903699642, "count": 84, "self": 37.12785239201821, "children": { "TorchPPOOptimizer.update": { "total": 55.45495664497821, "count": 4281, "self": 55.45495664497821 } } } } } } }, "trainer_threads": { "total": 1.1060001270379871e-06, "count": 1, "self": 1.1060001270379871e-06 }, "TrainerController._save_models": { "total": 0.08249063699986436, "count": 1, "self": 0.000953740000113612, "children": { "RLTrainer._checkpoint": { "total": 0.08153689699975075, "count": 1, "self": 0.08153689699975075 } } } } } } }