{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9440094828605652, "min": 0.9366451501846313, "max": 2.8452396392822266, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9044.5546875, "min": 9044.5546875, "max": 29138.099609375, "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": 13.122218132019043, "min": 0.46831512451171875, "max": 13.122218132019043, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2558.83251953125, "min": 90.85313415527344, "max": 2672.5048828125, "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": 0.09730276524308412, "min": 0.09396661060759279, "max": 0.10201459738420775, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3892110609723365, "min": 0.3786420467655537, "max": 0.5001505426123974, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16500681512715187, "min": 0.13036287206111025, "max": 0.2812592235057294, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6600272605086075, "min": 0.521451488244441, "max": 1.406296117528647, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.00029188200270599996, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.0013851600382799997, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.102694, "min": 0.102694, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.410776, "min": 0.410776, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970600000001, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.0, "min": 3.9545454545454546, "max": 26.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1144.0, "min": 174.0, "max": 1426.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.0, "min": 3.9545454545454546, "max": 26.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1144.0, "min": 174.0, "max": 1426.0, "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": "1689020461", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1689021160" }, "total": 698.5491055519999, "count": 1, "self": 0.4313148089999004, "children": { "run_training.setup": { "total": 0.04318466699999135, "count": 1, "self": 0.04318466699999135 }, "TrainerController.start_learning": { "total": 698.074606076, "count": 1, "self": 0.5858295280226002, "children": { "TrainerController._reset_env": { "total": 5.134081325999887, "count": 1, "self": 5.134081325999887 }, "TrainerController.advance": { "total": 692.1959320259774, "count": 18204, "self": 0.2829023139868241, "children": { "env_step": { "total": 691.9130297119906, "count": 18204, "self": 573.200112884976, "children": { "SubprocessEnvManager._take_step": { "total": 118.4378713640059, "count": 18204, "self": 1.8025861599859354, "children": { "TorchPolicy.evaluate": { "total": 116.63528520401997, "count": 18204, "self": 116.63528520401997 } } }, "workers": { "total": 0.27504546300872335, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 696.1997184149831, "count": 18204, "is_parallel": true, "self": 437.3420894659706, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005807860000004439, "count": 1, "is_parallel": true, "self": 0.00400479799986897, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018030620001354691, "count": 10, "is_parallel": true, "self": 0.0018030620001354691 } } }, "UnityEnvironment.step": { "total": 0.06770202399991376, "count": 1, "is_parallel": true, "self": 0.0006685159999051393, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043763600001511804, "count": 1, "is_parallel": true, "self": 0.00043763600001511804 }, "communicator.exchange": { "total": 0.06416137600001548, "count": 1, "is_parallel": true, "self": 0.06416137600001548 }, "steps_from_proto": { "total": 0.002434495999978026, "count": 1, "is_parallel": true, "self": 0.0005195759999878646, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019149199999901612, "count": 10, "is_parallel": true, "self": 0.0019149199999901612 } } } } } } }, "UnityEnvironment.step": { "total": 258.85762894901245, "count": 18203, "is_parallel": true, "self": 10.820326757036128, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2087550059935666, "count": 18203, "is_parallel": true, "self": 5.2087550059935666 }, "communicator.exchange": { "total": 206.66776427598631, "count": 18203, "is_parallel": true, "self": 206.66776427598631 }, "steps_from_proto": { "total": 36.16078290999644, "count": 18203, "is_parallel": true, "self": 6.562694461976321, "children": { "_process_rank_one_or_two_observation": { "total": 29.59808844802012, "count": 182030, "is_parallel": true, "self": 29.59808844802012 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011732600000868842, "count": 1, "self": 0.00011732600000868842, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 688.8906897730203, "count": 459813, "is_parallel": true, "self": 9.190304647007338, "children": { "process_trajectory": { "total": 256.4961171010127, "count": 459813, "is_parallel": true, "self": 255.09821634001264, "children": { "RLTrainer._checkpoint": { "total": 1.3979007610000735, "count": 4, "is_parallel": true, "self": 1.3979007610000735 } } }, "_update_policy": { "total": 423.20426802500026, "count": 90, "is_parallel": true, "self": 143.7468581700175, "children": { "TorchPPOOptimizer.update": { "total": 279.45740985498276, "count": 21413, "is_parallel": true, "self": 279.45740985498276 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15864587000010033, "count": 1, "self": 0.0010031930003151501, "children": { "RLTrainer._checkpoint": { "total": 0.15764267699978518, "count": 1, "self": 0.15764267699978518 } } } } } } }