{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.8615310192108154, "min": 2.8615310192108154, "max": 2.886932373046875, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 29462.322265625, "min": 29462.322265625, "max": 29596.830078125, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.0002551078796387, "min": 0.3444308638572693, "max": 1.0002551078796387, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 205.05230712890625, "min": 66.81958770751953, "max": 205.05230712890625, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07447843391210864, "min": 0.06754586317515979, "max": 0.07447843391210864, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.37239216956054316, "min": 0.27018345270063915, "max": 0.37239216956054316, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1379221051347022, "min": 0.12952202485244282, "max": 0.1379221051347022, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.689610525673511, "min": 0.5180880994097713, "max": 0.689610525673511, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.3440076560000008e-05, "min": 2.3440076560000008e-05, "max": 7.294002706e-05, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00011720038280000003, "min": 0.00011720038280000003, "max": 0.00029176010824, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12344000000000002, "min": 0.12344000000000002, "max": 0.17294, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6172000000000001, "min": 0.6172000000000001, "max": 0.69176, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011796560000000003, "min": 0.0011796560000000003, "max": 0.003649706, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005898280000000001, "min": 0.005898280000000001, "max": 0.014598824, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 3.5090909090909093, "min": 3.4545454545454546, "max": 3.5090909090909093, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 193.0, "min": 152.0, "max": 193.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 3.5090909090909093, "min": 3.4545454545454546, "max": 3.5090909090909093, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 193.0, "min": 152.0, "max": 193.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1698882283", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698882343" }, "total": 59.73805357700007, "count": 1, "self": 0.49389270800008944, "children": { "run_training.setup": { "total": 0.061190871000007974, "count": 1, "self": 0.061190871000007974 }, "TrainerController.start_learning": { "total": 59.182969997999976, "count": 1, "self": 0.12430316999814295, "children": { "TrainerController._reset_env": { "total": 1.642471019000027, "count": 1, "self": 1.642471019000027 }, "TrainerController.advance": { "total": 57.26187426100182, "count": 1869, "self": 0.04219935800199437, "children": { "env_step": { "total": 57.21967490299983, "count": 1869, "self": 44.71164813499695, "children": { "SubprocessEnvManager._take_step": { "total": 12.46738535400516, "count": 1869, "self": 0.20917416900761054, "children": { "TorchPolicy.evaluate": { "total": 12.258211184997549, "count": 1869, "self": 12.258211184997549 } } }, "workers": { "total": 0.0406414139977187, "count": 1869, "self": 0.0, "children": { "worker_root": { "total": 58.81580348500154, "count": 1869, "is_parallel": true, "self": 27.424210969001706, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006928752000021632, "count": 1, "is_parallel": true, "self": 0.004879679000055148, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020490729999664836, "count": 10, "is_parallel": true, "self": 0.0020490729999664836 } } }, "UnityEnvironment.step": { "total": 0.043806754999991426, "count": 1, "is_parallel": true, "self": 0.0007341790000054971, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004379970000627509, "count": 1, "is_parallel": true, "self": 0.0004379970000627509 }, "communicator.exchange": { "total": 0.04029802499997004, "count": 1, "is_parallel": true, "self": 0.04029802499997004 }, "steps_from_proto": { "total": 0.0023365539999531393, "count": 1, "is_parallel": true, "self": 0.0004207449997011281, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019158090002520112, "count": 10, "is_parallel": true, "self": 0.0019158090002520112 } } } } } } }, "UnityEnvironment.step": { "total": 31.391592515999832, "count": 1868, "is_parallel": true, "self": 1.4307371239937083, "children": { "UnityEnvironment._generate_step_input": { "total": 0.7480539689992156, "count": 1868, "is_parallel": true, "self": 0.7480539689992156 }, "communicator.exchange": { "total": 24.639800272002162, "count": 1868, "is_parallel": true, "self": 24.639800272002162 }, "steps_from_proto": { "total": 4.573001151004746, "count": 1868, "is_parallel": true, "self": 0.8862845460037079, "children": { "_process_rank_one_or_two_observation": { "total": 3.6867166050010383, "count": 18680, "is_parallel": true, "self": 3.6867166050010383 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00032397999996192084, "count": 1, "self": 0.00032397999996192084, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 56.799203519998514, "count": 57640, "is_parallel": true, "self": 1.3539879359991573, "children": { "process_trajectory": { "total": 32.28456957999913, "count": 57640, "is_parallel": true, "self": 32.28456957999913 }, "_update_policy": { "total": 23.160646004000228, "count": 9, "is_parallel": true, "self": 6.818244943000991, "children": { "TorchPPOOptimizer.update": { "total": 16.342401060999237, "count": 456, "is_parallel": true, "self": 16.342401060999237 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1539975680000225, "count": 1, "self": 0.001023415000076966, "children": { "RLTrainer._checkpoint": { "total": 0.15297415299994555, "count": 1, "self": 0.15297415299994555 } } } } } } }