{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.035966396331787, "min": 1.035966396331787, "max": 2.8404085636138916, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9891.4072265625, "min": 9891.4072265625, "max": 29119.869140625, "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": 12.859362602233887, "min": 0.44797107577323914, "max": 12.859362602233887, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2507.57568359375, "min": 86.90638732910156, "max": 2589.83251953125, "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": 0.06914947379613401, "min": 0.06744812900019871, "max": 0.07141088696868489, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27659789518453604, "min": 0.26995080903706026, "max": 0.3566109991964243, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19330633746131376, "min": 0.09646881941332729, "max": 0.2682801044673896, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.773225349845255, "min": 0.38587527765330915, "max": 1.1611877828544261, "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": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "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": 25.59090909090909, "min": 3.7954545454545454, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 167.0, "max": 1400.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.7954545454545454, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 167.0, "max": 1400.0, "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": "1680766067", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1680767358" }, "total": 1291.582291183, "count": 1, "self": 0.4338516660000096, "children": { "run_training.setup": { "total": 0.11938844399998061, "count": 1, "self": 0.11938844399998061 }, "TrainerController.start_learning": { "total": 1291.0290510730001, "count": 1, "self": 0.6279949000097531, "children": { "TrainerController._reset_env": { "total": 4.025797104999981, "count": 1, "self": 4.025797104999981 }, "TrainerController.advance": { "total": 1286.2446367309904, "count": 18200, "self": 0.31883964498820205, "children": { "env_step": { "total": 1285.9257970860021, "count": 18200, "self": 1158.5047181590073, "children": { "SubprocessEnvManager._take_step": { "total": 127.09953934999669, "count": 18200, "self": 1.69668064198504, "children": { "TorchPolicy.evaluate": { "total": 125.40285870801165, "count": 18200, "self": 125.40285870801165 } } }, "workers": { "total": 0.3215395769981342, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 1289.6728978269964, "count": 18200, "is_parallel": true, "self": 1045.1259035170021, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005494016999989526, "count": 1, "is_parallel": true, "self": 0.003922481999950378, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015715350000391481, "count": 10, "is_parallel": true, "self": 0.0015715350000391481 } } }, "UnityEnvironment.step": { "total": 0.03402027599997837, "count": 1, "is_parallel": true, "self": 0.0006599269999583157, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035770099998444493, "count": 1, "is_parallel": true, "self": 0.00035770099998444493 }, "communicator.exchange": { "total": 0.03101849300003323, "count": 1, "is_parallel": true, "self": 0.03101849300003323 }, "steps_from_proto": { "total": 0.0019841550000023744, "count": 1, "is_parallel": true, "self": 0.0004121230000464493, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015720319999559251, "count": 10, "is_parallel": true, "self": 0.0015720319999559251 } } } } } } }, "UnityEnvironment.step": { "total": 244.54699430999432, "count": 18199, "is_parallel": true, "self": 10.268306032995724, "children": { "UnityEnvironment._generate_step_input": { "total": 5.501963746017168, "count": 18199, "is_parallel": true, "self": 5.501963746017168 }, "communicator.exchange": { "total": 197.13264187798444, "count": 18199, "is_parallel": true, "self": 197.13264187798444 }, "steps_from_proto": { "total": 31.644082652996985, "count": 18199, "is_parallel": true, "self": 6.442865358990218, "children": { "_process_rank_one_or_two_observation": { "total": 25.201217294006767, "count": 181990, "is_parallel": true, "self": 25.201217294006767 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001596040001459187, "count": 1, "self": 0.0001596040001459187, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1283.1185519030155, "count": 374456, "is_parallel": true, "self": 9.393534138004725, "children": { "process_trajectory": { "total": 245.87285643201136, "count": 374456, "is_parallel": true, "self": 245.15760749701116, "children": { "RLTrainer._checkpoint": { "total": 0.7152489350002043, "count": 4, "is_parallel": true, "self": 0.7152489350002043 } } }, "_update_policy": { "total": 1027.8521613329995, "count": 90, "is_parallel": true, "self": 501.701569937999, "children": { "TorchPPOOptimizer.update": { "total": 526.1505913950004, "count": 45870, "is_parallel": true, "self": 526.1505913950004 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13046273299983113, "count": 1, "self": 0.0008734089997233241, "children": { "RLTrainer._checkpoint": { "total": 0.1295893240001078, "count": 1, "self": 0.1295893240001078 } } } } } } }