{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9852136969566345, "min": 0.9852136969566345, "max": 2.8588531017303467, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9406.8203125, "min": 9406.8203125, "max": 29277.513671875, "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": 12.714470863342285, "min": 0.21063563227653503, "max": 12.714470863342285, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2479.32177734375, "min": 40.863311767578125, "max": 2577.29248046875, "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": 0.0667423048084054, "min": 0.060287939773058734, "max": 0.07498055994980021, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2669692192336216, "min": 0.24115175909223494, "max": 0.3620912883205379, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22288527967883093, "min": 0.10342249176556281, "max": 0.2693491629963996, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8915411187153237, "min": 0.41368996706225125, "max": 1.3355615618182164, "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": 25.09090909090909, "min": 2.7954545454545454, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1104.0, "min": 123.0, "max": 1377.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.09090909090909, "min": 2.7954545454545454, "max": 25.204545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1104.0, "min": 123.0, "max": 1377.0, "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": "1702202458", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702202934" }, "total": 475.5332278709999, "count": 1, "self": 0.44484166500001265, "children": { "run_training.setup": { "total": 0.0574580039999546, "count": 1, "self": 0.0574580039999546 }, "TrainerController.start_learning": { "total": 475.0309282019999, "count": 1, "self": 0.6075072270033388, "children": { "TrainerController._reset_env": { "total": 3.5801640050000287, "count": 1, "self": 3.5801640050000287 }, "TrainerController.advance": { "total": 470.75309785499655, "count": 18199, "self": 0.29684232100487407, "children": { "env_step": { "total": 470.4562555339917, "count": 18199, "self": 318.6230920309546, "children": { "SubprocessEnvManager._take_step": { "total": 151.52254029601147, "count": 18199, "self": 1.466731725025852, "children": { "TorchPolicy.evaluate": { "total": 150.05580857098562, "count": 18199, "self": 150.05580857098562 } } }, "workers": { "total": 0.3106232070256283, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 473.7399698120132, "count": 18199, "is_parallel": true, "self": 232.40422552300788, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0049189630000228135, "count": 1, "is_parallel": true, "self": 0.003582848000064587, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013361149999582267, "count": 10, "is_parallel": true, "self": 0.0013361149999582267 } } }, "UnityEnvironment.step": { "total": 0.03782997299992985, "count": 1, "is_parallel": true, "self": 0.002603342999805136, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003380220000508416, "count": 1, "is_parallel": true, "self": 0.0003380220000508416 }, "communicator.exchange": { "total": 0.03286802600007377, "count": 1, "is_parallel": true, "self": 0.03286802600007377 }, "steps_from_proto": { "total": 0.002020582000000104, "count": 1, "is_parallel": true, "self": 0.00038440000002992747, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016361819999701765, "count": 10, "is_parallel": true, "self": 0.0016361819999701765 } } } } } } }, "UnityEnvironment.step": { "total": 241.33574428900533, "count": 18198, "is_parallel": true, "self": 10.54160931503884, "children": { "UnityEnvironment._generate_step_input": { "total": 5.421707702989352, "count": 18198, "is_parallel": true, "self": 5.421707702989352 }, "communicator.exchange": { "total": 191.5735251709849, "count": 18198, "is_parallel": true, "self": 191.5735251709849 }, "steps_from_proto": { "total": 33.79890209999223, "count": 18198, "is_parallel": true, "self": 6.450688426001989, "children": { "_process_rank_one_or_two_observation": { "total": 27.348213673990244, "count": 181980, "is_parallel": true, "self": 27.348213673990244 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.000161208000008628, "count": 1, "self": 0.000161208000008628, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 466.766539898098, "count": 502089, "is_parallel": true, "self": 10.844546133102654, "children": { "process_trajectory": { "total": 264.7175829109965, "count": 502089, "is_parallel": true, "self": 264.25923646499655, "children": { "RLTrainer._checkpoint": { "total": 0.45834644599995045, "count": 4, "is_parallel": true, "self": 0.45834644599995045 } } }, "_update_policy": { "total": 191.20441085399887, "count": 90, "is_parallel": true, "self": 55.916943809002646, "children": { "TorchPPOOptimizer.update": { "total": 135.28746704499622, "count": 4587, "is_parallel": true, "self": 135.28746704499622 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08999790699999721, "count": 1, "self": 0.0008967920000486629, "children": { "RLTrainer._checkpoint": { "total": 0.08910111499994855, "count": 1, "self": 0.08910111499994855 } } } } } } }