{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.3238823413848877, "min": 1.3238823413848877, "max": 2.8832128047943115, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12640.4287109375, "min": 12640.4287109375, "max": 29558.697265625, "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": 10.69958782196045, "min": 0.20849844813346863, "max": 10.69958782196045, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2086.419677734375, "min": 40.448699951171875, "max": 2128.146484375, "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": 23.068181818181817, "min": 3.522727272727273, "max": 23.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1015.0, "min": 155.0, "max": 1240.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.068181818181817, "min": 3.522727272727273, "max": 23.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1015.0, "min": 155.0, "max": 1240.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.09569611067184036, "min": 0.09168968751828833, "max": 0.10556506410801056, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.19139222134368072, "min": 0.18337937503657667, "max": 0.31467946409522446, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19962809035810186, "min": 0.11151569478081871, "max": 0.27155165326799835, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.3992561807162037, "min": 0.22303138956163743, "max": 0.7853984344093239, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.432097856000004e-06, "min": 6.432097856000004e-06, "max": 0.00029023200325600004, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.2864195712000008e-05, "min": 1.2864195712000008e-05, "max": 0.0007419960526679999, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10214399999999998, "min": 0.10214399999999998, "max": 0.196744, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20428799999999997, "min": 0.20428799999999997, "max": 0.5473319999999999, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001169856000000001, "min": 0.0001169856000000001, "max": 0.0048375256, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0002339712000000002, "min": 0.0002339712000000002, "max": 0.0123718668, "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": "1676382769", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676383311" }, "total": 542.2621346150002, "count": 1, "self": 0.4344580570002563, "children": { "run_training.setup": { "total": 0.1161793310000121, "count": 1, "self": 0.1161793310000121 }, "TrainerController.start_learning": { "total": 541.7114972269999, "count": 1, "self": 0.5745216280138266, "children": { "TrainerController._reset_env": { "total": 10.585251036999807, "count": 1, "self": 10.585251036999807 }, "TrainerController.advance": { "total": 530.4147566229865, "count": 18204, "self": 0.2961115799973868, "children": { "env_step": { "total": 530.1186450429891, "count": 18204, "self": 403.0111953469732, "children": { "SubprocessEnvManager._take_step": { "total": 126.82171233102144, "count": 18204, "self": 1.5306838310270905, "children": { "TorchPolicy.evaluate": { "total": 125.29102849999435, "count": 18204, "self": 26.85547324799495, "children": { "TorchPolicy.sample_actions": { "total": 98.4355552519994, "count": 18204, "self": 98.4355552519994 } } } } }, "workers": { "total": 0.2857373649944748, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 540.2089348609945, "count": 18204, "is_parallel": true, "self": 292.96357180201585, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010954927000057069, "count": 1, "is_parallel": true, "self": 0.003988411000591441, "children": { "_process_rank_one_or_two_observation": { "total": 0.006966515999465628, "count": 10, "is_parallel": true, "self": 0.006966515999465628 } } }, "UnityEnvironment.step": { "total": 0.0388726820001466, "count": 1, "is_parallel": true, "self": 0.0005583929998920212, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025489600011496805, "count": 1, "is_parallel": true, "self": 0.00025489600011496805 }, "communicator.exchange": { "total": 0.03624993900007212, "count": 1, "is_parallel": true, "self": 0.03624993900007212 }, "steps_from_proto": { "total": 0.0018094540000674897, "count": 1, "is_parallel": true, "self": 0.0004209200005789171, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013885339994885726, "count": 10, "is_parallel": true, "self": 0.0013885339994885726 } } } } } } }, "UnityEnvironment.step": { "total": 247.24536305897868, "count": 18203, "is_parallel": true, "self": 9.861512551933174, "children": { "UnityEnvironment._generate_step_input": { "total": 5.409648868005206, "count": 18203, "is_parallel": true, "self": 5.409648868005206 }, "communicator.exchange": { "total": 199.58086642902163, "count": 18203, "is_parallel": true, "self": 199.58086642902163 }, "steps_from_proto": { "total": 32.39333521001868, "count": 18203, "is_parallel": true, "self": 7.197601221012519, "children": { "_process_rank_one_or_two_observation": { "total": 25.195733989006158, "count": 182030, "is_parallel": true, "self": 25.195733989006158 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018581199992695474, "count": 1, "self": 0.00018581199992695474, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 525.9586517710036, "count": 514501, "is_parallel": true, "self": 13.117024436941165, "children": { "process_trajectory": { "total": 323.78573539606145, "count": 514501, "is_parallel": true, "self": 322.4582278500616, "children": { "RLTrainer._checkpoint": { "total": 1.3275075459998789, "count": 4, "is_parallel": true, "self": 1.3275075459998789 } } }, "_update_policy": { "total": 189.05589193800097, "count": 45, "is_parallel": true, "self": 59.427557878012976, "children": { "TorchPPOOptimizer.update": { "total": 129.628334059988, "count": 9177, "is_parallel": true, "self": 129.628334059988 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13678212699983305, "count": 1, "self": 0.0010491949999504868, "children": { "RLTrainer._checkpoint": { "total": 0.13573293199988257, "count": 1, "self": 0.13573293199988257 } } } } } } }