{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7300139665603638, "min": 0.7300139665603638, "max": 2.843945026397705, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6938.052734375, "min": 6938.052734375, "max": 29030.990234375, "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": 13.009978294372559, "min": 0.4213377833366394, "max": 13.009978294372559, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2536.94580078125, "min": 81.73953247070312, "max": 2623.17724609375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06895762257330466, "min": 0.06100233076688122, "max": 0.07405436843320928, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27583049029321866, "min": 0.25872326187570305, "max": 0.3648354349767461, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16403469147489352, "min": 0.15231087350505676, "max": 0.29296654082980805, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6561387658995741, "min": 0.609243494020227, "max": 1.4648327041490403, "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.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.Environment.CumulativeReward.mean": { "value": 25.727272727272727, "min": 4.136363636363637, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1132.0, "min": 182.0, "max": 1414.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.727272727272727, "min": 4.136363636363637, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1132.0, "min": 182.0, "max": 1414.0, "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": "1745309010", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/ippc-zq/miniconda3/envs/hf_drl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1745309194" }, "total": 183.930085436441, "count": 1, "self": 0.21775061264634132, "children": { "run_training.setup": { "total": 0.015120109543204308, "count": 1, "self": 0.015120109543204308 }, "TrainerController.start_learning": { "total": 183.69721471425146, "count": 1, "self": 0.14631875231862068, "children": { "TrainerController._reset_env": { "total": 1.3728843415156007, "count": 1, "self": 1.3728843415156007 }, "TrainerController.advance": { "total": 182.13395763467997, "count": 18192, "self": 0.1541950600221753, "children": { "env_step": { "total": 124.02047614008188, "count": 18192, "self": 92.10586133785546, "children": { "SubprocessEnvManager._take_step": { "total": 31.819391447119415, "count": 18192, "self": 0.5148606086149812, "children": { "TorchPolicy.evaluate": { "total": 31.304530838504434, "count": 18192, "self": 31.304530838504434 } } }, "workers": { "total": 0.09522335510700941, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 183.3422796688974, "count": 18192, "is_parallel": true, "self": 101.98661585524678, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013205315917730331, "count": 1, "is_parallel": true, "self": 0.0003907661885023117, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009297654032707214, "count": 10, "is_parallel": true, "self": 0.0009297654032707214 } } }, "UnityEnvironment.step": { "total": 0.014777534641325474, "count": 1, "is_parallel": true, "self": 0.00033060554414987564, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025530438870191574, "count": 1, "is_parallel": true, "self": 0.00025530438870191574 }, "communicator.exchange": { "total": 0.013186708092689514, "count": 1, "is_parallel": true, "self": 0.013186708092689514 }, "steps_from_proto": { "total": 0.0010049166157841682, "count": 1, "is_parallel": true, "self": 0.00020704232156276703, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007978742942214012, "count": 10, "is_parallel": true, "self": 0.0007978742942214012 } } } } } } }, "UnityEnvironment.step": { "total": 81.35566381365061, "count": 18191, "is_parallel": true, "self": 3.4688938101753592, "children": { "UnityEnvironment._generate_step_input": { "total": 1.9815410012379289, "count": 18191, "is_parallel": true, "self": 1.9815410012379289 }, "communicator.exchange": { "total": 65.2415582202375, "count": 18191, "is_parallel": true, "self": 65.2415582202375 }, "steps_from_proto": { "total": 10.663670781999826, "count": 18191, "is_parallel": true, "self": 2.086039500311017, "children": { "_process_rank_one_or_two_observation": { "total": 8.57763128168881, "count": 181910, "is_parallel": true, "self": 8.57763128168881 } } } } } } } } } } }, "trainer_advance": { "total": 57.959286434575915, "count": 18192, "self": 0.16834591049700975, "children": { "process_trajectory": { "total": 12.684624137356877, "count": 18192, "self": 12.45142443291843, "children": { "RLTrainer._checkpoint": { "total": 0.23319970443844795, "count": 4, "self": 0.23319970443844795 } } }, "_update_policy": { "total": 45.10631638672203, "count": 90, "self": 18.47339269798249, "children": { "TorchPPOOptimizer.update": { "total": 26.632923688739538, "count": 4587, "self": 26.632923688739538 } } } } } } }, "trainer_threads": { "total": 6.202608346939087e-07, "count": 1, "self": 6.202608346939087e-07 }, "TrainerController._save_models": { "total": 0.04405336547642946, "count": 1, "self": 0.0005346359685063362, "children": { "RLTrainer._checkpoint": { "total": 0.043518729507923126, "count": 1, "self": 0.043518729507923126 } } } } } } }