{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.4640839695930481, "min": 0.46335798501968384, "max": 2.8744521141052246, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4778.20849609375, "min": 4420.2529296875, "max": 29342.408203125, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.271677017211914, "min": 0.40419891476631165, "max": 14.420598030090332, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2925.69384765625, "min": 78.41458892822266, "max": 2949.749755859375, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06806659528736811, "min": 0.05760496456111343, "max": 0.07640866107962496, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3403329764368405, "min": 0.2304198582444537, "max": 0.38008534068313904, "count": 200 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1701448224046651, "min": 0.1142922752518572, "max": 0.2989402155081431, "count": 200 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8507241120233255, "min": 0.4571691010074288, "max": 1.4947010775407155, "count": 200 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032997656000039e-07, "min": 7.032997656000039e-07, "max": 0.00029918820027059994, "count": 200 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.5164988280000196e-06, "min": 3.5164988280000196e-06, "max": 0.0014885160038279998, "count": 200 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10023440000000002, "min": 0.10023440000000002, "max": 0.1997294, "count": 200 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5011720000000001, "min": 0.4029176, "max": 0.996172, "count": 200 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.1696560000000067e-05, "min": 2.1696560000000067e-05, "max": 0.004986497059999999, "count": 200 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00010848280000000034, "min": 0.00010848280000000034, "max": 0.024808982800000004, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.345454545454544, "min": 3.4318181818181817, "max": 28.581818181818182, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1504.0, "min": 151.0, "max": 1572.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.345454545454544, "min": 3.4318181818181817, "max": 28.581818181818182, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1504.0, "min": 151.0, "max": 1572.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1770593467", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1770597861" }, "total": 4394.018748836999, "count": 1, "self": 0.47660773399820755, "children": { "run_training.setup": { "total": 0.029923408000286145, "count": 1, "self": 0.029923408000286145 }, "TrainerController.start_learning": { "total": 4393.512217695001, "count": 1, "self": 3.7676694411093195, "children": { "TrainerController._reset_env": { "total": 1.7913107260001198, "count": 1, "self": 1.7913107260001198 }, "TrainerController.advance": { "total": 4387.869930687892, "count": 181864, "self": 3.950413664205371, "children": { "env_step": { "total": 3192.8163815699327, "count": 181864, "self": 2491.976419407858, "children": { "SubprocessEnvManager._take_step": { "total": 698.536891151999, "count": 181864, "self": 12.877168777048155, "children": { "TorchPolicy.evaluate": { "total": 685.6597223749509, "count": 181864, "self": 685.6597223749509 } } }, "workers": { "total": 2.303071010075655, "count": 181864, "self": 0.0, "children": { "worker_root": { "total": 4378.054228119862, "count": 181864, "is_parallel": true, "self": 2193.0227901438525, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021330879999368335, "count": 1, "is_parallel": true, "self": 0.000690076999944722, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014430109999921115, "count": 10, "is_parallel": true, "self": 0.0014430109999921115 } } }, "UnityEnvironment.step": { "total": 0.035167684000043664, "count": 1, "is_parallel": true, "self": 0.0005844800002705597, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004027129998576129, "count": 1, "is_parallel": true, "self": 0.0004027129998576129 }, "communicator.exchange": { "total": 0.03236229899994214, "count": 1, "is_parallel": true, "self": 0.03236229899994214 }, "steps_from_proto": { "total": 0.001818191999973351, "count": 1, "is_parallel": true, "self": 0.00035864699975718395, "children": { "_process_rank_one_or_two_observation": { "total": 0.001459545000216167, "count": 10, "is_parallel": true, "self": 0.001459545000216167 } } } } } } }, "UnityEnvironment.step": { "total": 2185.03143797601, "count": 181863, "is_parallel": true, "self": 101.07277186692863, "children": { "UnityEnvironment._generate_step_input": { "total": 54.456352131190215, "count": 181863, "is_parallel": true, "self": 54.456352131190215 }, "communicator.exchange": { "total": 1666.2199322010697, "count": 181863, "is_parallel": true, "self": 1666.2199322010697 }, "steps_from_proto": { "total": 363.28238177682124, "count": 181863, "is_parallel": true, "self": 67.3950197194572, "children": { "_process_rank_one_or_two_observation": { "total": 295.88736205736404, "count": 1818630, "is_parallel": true, "self": 295.88736205736404 } } } } } } } } } } }, "trainer_advance": { "total": 1191.1031354537536, "count": 181864, "self": 4.616626632641783, "children": { "process_trajectory": { "total": 259.5865856991172, "count": 181864, "self": 256.1810363451191, "children": { "RLTrainer._checkpoint": { "total": 3.40554935399814, "count": 40, "self": 3.40554935399814 } } }, "_update_policy": { "total": 926.8999231219946, "count": 909, "self": 378.49098049994836, "children": { "TorchPPOOptimizer.update": { "total": 548.4089426220462, "count": 46356, "self": 548.4089426220462 } } } } } } }, "trainer_threads": { "total": 1.0670000847312622e-06, "count": 1, "self": 1.0670000847312622e-06 }, "TrainerController._save_models": { "total": 0.08330577299966535, "count": 1, "self": 0.0007299330000023474, "children": { "RLTrainer._checkpoint": { "total": 0.082575839999663, "count": 1, "self": 0.082575839999663 } } } } } } }