{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0671510696411133, "min": 1.0557539463043213, "max": 2.8721261024475098, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10212.6357421875, "min": 10212.6357421875, "max": 29445.037109375, "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": 12.501420021057129, "min": 0.35908225178718567, "max": 12.501420021057129, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2437.77685546875, "min": 69.66195678710938, "max": 2541.619140625, "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": 0.0684011133478135, "min": 0.06019873213959976, "max": 0.07373807844158044, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.273604453391254, "min": 0.24079492855839904, "max": 0.3686903922079022, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2336552064208423, "min": 0.13049544141554803, "max": 0.2771460945699729, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9346208256833692, "min": 0.5219817656621921, "max": 1.333038115326096, "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": 24.636363636363637, "min": 3.5454545454545454, "max": 24.836363636363636, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1084.0, "min": 156.0, "max": 1366.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.636363636363637, "min": 3.5454545454545454, "max": 24.836363636363636, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1084.0, "min": 156.0, "max": 1366.0, "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": "1706704908", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706705556" }, "total": 648.1286294379997, "count": 1, "self": 0.6038745660007407, "children": { "run_training.setup": { "total": 0.09402988399961032, "count": 1, "self": 0.09402988399961032 }, "TrainerController.start_learning": { "total": 647.4307249879994, "count": 1, "self": 0.8831739979214035, "children": { "TrainerController._reset_env": { "total": 5.652500455000336, "count": 1, "self": 5.652500455000336 }, "TrainerController.advance": { "total": 640.791398011077, "count": 18201, "self": 0.4594365610673776, "children": { "env_step": { "total": 640.3319614500097, "count": 18201, "self": 495.30910211603623, "children": { "SubprocessEnvManager._take_step": { "total": 144.5699696059619, "count": 18201, "self": 2.7443479819621643, "children": { "TorchPolicy.evaluate": { "total": 141.82562162399972, "count": 18201, "self": 141.82562162399972 } } }, "workers": { "total": 0.4528897280115416, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 645.1703953120123, "count": 18201, "is_parallel": true, "self": 302.2592878410569, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008571221000238438, "count": 1, "is_parallel": true, "self": 0.005413152000073751, "children": { "_process_rank_one_or_two_observation": { "total": 0.003158069000164687, "count": 10, "is_parallel": true, "self": 0.003158069000164687 } } }, "UnityEnvironment.step": { "total": 0.05513717399935558, "count": 1, "is_parallel": true, "self": 0.0007876019990362693, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005362820002119406, "count": 1, "is_parallel": true, "self": 0.0005362820002119406 }, "communicator.exchange": { "total": 0.051367320000281325, "count": 1, "is_parallel": true, "self": 0.051367320000281325 }, "steps_from_proto": { "total": 0.0024459699998260476, "count": 1, "is_parallel": true, "self": 0.00048566000168648316, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019603099981395644, "count": 10, "is_parallel": true, "self": 0.0019603099981395644 } } } } } } }, "UnityEnvironment.step": { "total": 342.91110747095536, "count": 18200, "is_parallel": true, "self": 15.658435675041801, "children": { "UnityEnvironment._generate_step_input": { "total": 8.258940915947278, "count": 18200, "is_parallel": true, "self": 8.258940915947278 }, "communicator.exchange": { "total": 271.5007502259996, "count": 18200, "is_parallel": true, "self": 271.5007502259996 }, "steps_from_proto": { "total": 47.4929806539667, "count": 18200, "is_parallel": true, "self": 9.666245327725846, "children": { "_process_rank_one_or_two_observation": { "total": 37.82673532624085, "count": 182000, "is_parallel": true, "self": 37.82673532624085 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00033636700027273037, "count": 1, "self": 0.00033636700027273037, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 633.2058367510108, "count": 824519, "is_parallel": true, "self": 19.740536227875964, "children": { "process_trajectory": { "total": 328.8676274411364, "count": 824519, "is_parallel": true, "self": 327.85980236913565, "children": { "RLTrainer._checkpoint": { "total": 1.0078250720007418, "count": 4, "is_parallel": true, "self": 1.0078250720007418 } } }, "_update_policy": { "total": 284.59767308199844, "count": 90, "is_parallel": true, "self": 82.86512223002501, "children": { "TorchPPOOptimizer.update": { "total": 201.73255085197343, "count": 4587, "is_parallel": true, "self": 201.73255085197343 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1033161570003358, "count": 1, "self": 0.0014259889994718833, "children": { "RLTrainer._checkpoint": { "total": 0.10189016800086392, "count": 1, "self": 0.10189016800086392 } } } } } } }