{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0621728897094727, "min": 1.0507895946502686, "max": 2.8593006134033203, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10270.1494140625, "min": 10270.1494140625, "max": 29376.455078125, "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": 13.413555145263672, "min": 0.4328593611717224, "max": 13.413555145263672, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2615.643310546875, "min": 83.97471618652344, "max": 2735.6513671875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06954942093722696, "min": 0.06468537034154138, "max": 0.07774804228877959, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27819768374890785, "min": 0.2698470164893889, "max": 0.36796645949053686, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20373382170995077, "min": 0.13509616263977747, "max": 0.2898427351432688, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8149352868398031, "min": 0.5403846505591099, "max": 1.449213675716344, "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": 26.25, "min": 3.9545454545454546, "max": 26.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1155.0, "min": 174.0, "max": 1465.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.25, "min": 3.9545454545454546, "max": 26.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1155.0, "min": 174.0, "max": 1465.0, "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": "1722635815", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722636282" }, "total": 467.08031528499987, "count": 1, "self": 0.4527869410001131, "children": { "run_training.setup": { "total": 0.06122800799994366, "count": 1, "self": 0.06122800799994366 }, "TrainerController.start_learning": { "total": 466.5663003359998, "count": 1, "self": 0.5549220719949517, "children": { "TrainerController._reset_env": { "total": 3.5293553490000704, "count": 1, "self": 3.5293553490000704 }, "TrainerController.advance": { "total": 462.35630882000464, "count": 18225, "self": 0.26820341200436815, "children": { "env_step": { "total": 462.0881054080003, "count": 18225, "self": 296.2454240570114, "children": { "SubprocessEnvManager._take_step": { "total": 165.569293983006, "count": 18225, "self": 1.4726673510012915, "children": { "TorchPolicy.evaluate": { "total": 164.0966266320047, "count": 18225, "self": 164.0966266320047 } } }, "workers": { "total": 0.27338736798287755, "count": 18225, "self": 0.0, "children": { "worker_root": { "total": 465.3642744100007, "count": 18225, "is_parallel": true, "self": 248.88553103099252, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005229529000189359, "count": 1, "is_parallel": true, "self": 0.003676488000110112, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015530410000792472, "count": 10, "is_parallel": true, "self": 0.0015530410000792472 } } }, "UnityEnvironment.step": { "total": 0.04508812299991405, "count": 1, "is_parallel": true, "self": 0.0006585109999832639, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003642089998265874, "count": 1, "is_parallel": true, "self": 0.0003642089998265874 }, "communicator.exchange": { "total": 0.041908669000122245, "count": 1, "is_parallel": true, "self": 0.041908669000122245 }, "steps_from_proto": { "total": 0.0021567339999819524, "count": 1, "is_parallel": true, "self": 0.00046746099974370736, "children": { "_process_rank_one_or_two_observation": { "total": 0.001689273000238245, "count": 10, "is_parallel": true, "self": 0.001689273000238245 } } } } } } }, "UnityEnvironment.step": { "total": 216.47874337900816, "count": 18224, "is_parallel": true, "self": 10.174809674987273, "children": { "UnityEnvironment._generate_step_input": { "total": 5.1458905730169135, "count": 18224, "is_parallel": true, "self": 5.1458905730169135 }, "communicator.exchange": { "total": 168.57056614201292, "count": 18224, "is_parallel": true, "self": 168.57056614201292 }, "steps_from_proto": { "total": 32.58747698899106, "count": 18224, "is_parallel": true, "self": 6.2353875069520655, "children": { "_process_rank_one_or_two_observation": { "total": 26.35208948203899, "count": 182240, "is_parallel": true, "self": 26.35208948203899 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015402700000777259, "count": 1, "self": 0.00015402700000777259, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.5391220489337, "count": 599890, "is_parallel": true, "self": 12.227656081963914, "children": { "process_trajectory": { "total": 264.3964657069696, "count": 599890, "is_parallel": true, "self": 263.3000031319698, "children": { "RLTrainer._checkpoint": { "total": 1.096462574999805, "count": 4, "is_parallel": true, "self": 1.096462574999805 } } }, "_update_policy": { "total": 180.91500026000017, "count": 90, "is_parallel": true, "self": 58.189634837995754, "children": { "TorchPPOOptimizer.update": { "total": 122.72536542200442, "count": 4584, "is_parallel": true, "self": 122.72536542200442 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12556006800014075, "count": 1, "self": 0.000951400000076319, "children": { "RLTrainer._checkpoint": { "total": 0.12460866800006443, "count": 1, "self": 0.12460866800006443 } } } } } } }