{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9898553490638733, "min": 0.9872123599052429, "max": 2.8721883296966553, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9451.138671875, "min": 9451.138671875, "max": 29445.67578125, "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": 12.536450386047363, "min": 0.29756423830986023, "max": 12.538382530212402, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2444.60791015625, "min": 57.72746276855469, "max": 2557.830078125, "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": 0.07195115317510642, "min": 0.0613162228997395, "max": 0.07617167744733616, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2878046127004257, "min": 0.256827344703625, "max": 0.3594081038928719, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24117908371137636, "min": 0.08387925713802413, "max": 0.26983621847980166, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9647163348455055, "min": 0.33551702855209653, "max": 1.2757801127200032, "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": 24.204545454545453, "min": 2.7954545454545454, "max": 24.795454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1065.0, "min": 123.0, "max": 1347.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.204545454545453, "min": 2.7954545454545454, "max": 24.795454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1065.0, "min": 123.0, "max": 1347.0, "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": "1684870815", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684871285" }, "total": 469.56133938, "count": 1, "self": 0.842734503000031, "children": { "run_training.setup": { "total": 0.042406071000016254, "count": 1, "self": 0.042406071000016254 }, "TrainerController.start_learning": { "total": 468.67619880599995, "count": 1, "self": 0.609915781990992, "children": { "TrainerController._reset_env": { "total": 3.816429191999987, "count": 1, "self": 3.816429191999987 }, "TrainerController.advance": { "total": 464.0328816840089, "count": 18217, "self": 0.28893696700981764, "children": { "env_step": { "total": 463.74394471699907, "count": 18217, "self": 340.63498641598903, "children": { "SubprocessEnvManager._take_step": { "total": 122.8177015530024, "count": 18217, "self": 1.795141740006727, "children": { "TorchPolicy.evaluate": { "total": 121.02255981299567, "count": 18217, "self": 121.02255981299567 } } }, "workers": { "total": 0.29125674800764045, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 466.7312000590057, "count": 18217, "is_parallel": true, "self": 217.19802221699774, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005602129999999761, "count": 1, "is_parallel": true, "self": 0.0041608370000858486, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014412929999139124, "count": 10, "is_parallel": true, "self": 0.0014412929999139124 } } }, "UnityEnvironment.step": { "total": 0.04976658599997563, "count": 1, "is_parallel": true, "self": 0.0005963019999057906, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003819240000098034, "count": 1, "is_parallel": true, "self": 0.0003819240000098034 }, "communicator.exchange": { "total": 0.04680640200001562, "count": 1, "is_parallel": true, "self": 0.04680640200001562 }, "steps_from_proto": { "total": 0.001981958000044415, "count": 1, "is_parallel": true, "self": 0.00038292199997158605, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015990360000728288, "count": 10, "is_parallel": true, "self": 0.0015990360000728288 } } } } } } }, "UnityEnvironment.step": { "total": 249.53317784200794, "count": 18216, "is_parallel": true, "self": 9.766430027006322, "children": { "UnityEnvironment._generate_step_input": { "total": 5.369825343998855, "count": 18216, "is_parallel": true, "self": 5.369825343998855 }, "communicator.exchange": { "total": 201.42829633700143, "count": 18216, "is_parallel": true, "self": 201.42829633700143 }, "steps_from_proto": { "total": 32.96862613400134, "count": 18216, "is_parallel": true, "self": 6.361346101003164, "children": { "_process_rank_one_or_two_observation": { "total": 26.607280032998176, "count": 182160, "is_parallel": true, "self": 26.607280032998176 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014625900007558812, "count": 1, "self": 0.00014625900007558812, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 460.60320343997773, "count": 447862, "is_parallel": true, "self": 9.63815720195862, "children": { "process_trajectory": { "total": 250.9966665210183, "count": 447862, "is_parallel": true, "self": 249.35790389901825, "children": { "RLTrainer._checkpoint": { "total": 1.6387626220000584, "count": 4, "is_parallel": true, "self": 1.6387626220000584 } } }, "_update_policy": { "total": 199.9683797170008, "count": 90, "is_parallel": true, "self": 78.98294489099652, "children": { "TorchPPOOptimizer.update": { "total": 120.98543482600428, "count": 4587, "is_parallel": true, "self": 120.98543482600428 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2168258890000061, "count": 1, "self": 0.0011585900000454785, "children": { "RLTrainer._checkpoint": { "total": 0.21566729899996062, "count": 1, "self": 0.21566729899996062 } } } } } } }