{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8852657079696655, "min": 0.8852657079696655, "max": 2.8724265098571777, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8510.9443359375, "min": 8510.9443359375, "max": 29448.1171875, "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": 13.117223739624023, "min": 0.17131690680980682, "max": 13.229989051818848, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2557.858642578125, "min": 33.23548126220703, "max": 2686.8828125, "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": 0.06496412342062731, "min": 0.06325063151464694, "max": 0.0746592159095242, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25985649368250924, "min": 0.25300252605858775, "max": 0.37329607954762095, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21010771174641218, "min": 0.09710273614230876, "max": 0.29501613938048776, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8404308469856487, "min": 0.38841094456923503, "max": 1.3666443944663167, "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": 25.59090909090909, "min": 2.659090909090909, "max": 26.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 117.0, "max": 1413.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 2.659090909090909, "max": 26.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 117.0, "max": 1413.0, "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": "1701541857", "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": "1701542359" }, "total": 501.15616715400006, "count": 1, "self": 0.7581419510001979, "children": { "run_training.setup": { "total": 0.06108421699991595, "count": 1, "self": 0.06108421699991595 }, "TrainerController.start_learning": { "total": 500.33694098599995, "count": 1, "self": 0.6429549730047484, "children": { "TrainerController._reset_env": { "total": 3.2355265050000526, "count": 1, "self": 3.2355265050000526 }, "TrainerController.advance": { "total": 496.313211794995, "count": 18212, "self": 0.29566134599781435, "children": { "env_step": { "total": 496.0175504489972, "count": 18212, "self": 336.73496089199125, "children": { "SubprocessEnvManager._take_step": { "total": 158.96136893900245, "count": 18212, "self": 1.5332669850080265, "children": { "TorchPolicy.evaluate": { "total": 157.42810195399443, "count": 18212, "self": 157.42810195399443 } } }, "workers": { "total": 0.3212206180035082, "count": 18212, "self": 0.0, "children": { "worker_root": { "total": 498.7991862540139, "count": 18212, "is_parallel": true, "self": 243.76868221200914, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005738252000014654, "count": 1, "is_parallel": true, "self": 0.0042718199998716955, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014664320001429587, "count": 10, "is_parallel": true, "self": 0.0014664320001429587 } } }, "UnityEnvironment.step": { "total": 0.036746320000020205, "count": 1, "is_parallel": true, "self": 0.000674361000051249, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040873699992971524, "count": 1, "is_parallel": true, "self": 0.00040873699992971524 }, "communicator.exchange": { "total": 0.033467717000007724, "count": 1, "is_parallel": true, "self": 0.033467717000007724 }, "steps_from_proto": { "total": 0.002195505000031517, "count": 1, "is_parallel": true, "self": 0.0004510140000775209, "children": { "_process_rank_one_or_two_observation": { "total": 0.001744490999953996, "count": 10, "is_parallel": true, "self": 0.001744490999953996 } } } } } } }, "UnityEnvironment.step": { "total": 255.03050404200474, "count": 18211, "is_parallel": true, "self": 11.029199092980207, "children": { "UnityEnvironment._generate_step_input": { "total": 5.762065286008806, "count": 18211, "is_parallel": true, "self": 5.762065286008806 }, "communicator.exchange": { "total": 201.85243073800984, "count": 18211, "is_parallel": true, "self": 201.85243073800984 }, "steps_from_proto": { "total": 36.38680892500588, "count": 18211, "is_parallel": true, "self": 6.980994769037466, "children": { "_process_rank_one_or_two_observation": { "total": 29.405814155968415, "count": 182110, "is_parallel": true, "self": 29.405814155968415 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015299500000764965, "count": 1, "self": 0.00015299500000764965, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 492.04334143497044, "count": 528797, "is_parallel": true, "self": 11.484427731959045, "children": { "process_trajectory": { "total": 278.1115525190121, "count": 528797, "is_parallel": true, "self": 277.062612902012, "children": { "RLTrainer._checkpoint": { "total": 1.0489396170000873, "count": 4, "is_parallel": true, "self": 1.0489396170000873 } } }, "_update_policy": { "total": 202.4473611839993, "count": 90, "is_parallel": true, "self": 63.638033893997886, "children": { "TorchPPOOptimizer.update": { "total": 138.80932729000142, "count": 4587, "is_parallel": true, "self": 138.80932729000142 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14509471800010942, "count": 1, "self": 0.0013106270000662334, "children": { "RLTrainer._checkpoint": { "total": 0.1437840910000432, "count": 1, "self": 0.1437840910000432 } } } } } } }