{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.028181791305542, "min": 1.028181791305542, "max": 2.874800443649292, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9828.3896484375, "min": 9828.3896484375, "max": 29472.453125, "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": 12.454669952392578, "min": 0.26137423515319824, "max": 12.454669952392578, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2428.66064453125, "min": 50.70660400390625, "max": 2535.73193359375, "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.Losses.PolicyLoss.mean": { "value": 0.06428230685139401, "min": 0.06078527844984623, "max": 0.07131165862151914, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25712922740557603, "min": 0.25712922740557603, "max": 0.3520738658718947, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19814225724514795, "min": 0.1252805273534785, "max": 0.27650552099826287, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7925690289805918, "min": 0.501122109413914, "max": 1.3825276049913144, "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": 24.0, "min": 3.1818181818181817, "max": 24.98181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1056.0, "min": 140.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.0, "min": 3.1818181818181817, "max": 24.98181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1056.0, "min": 140.0, "max": 1374.0, "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": "1706882731", "python_version": "3.10.12 (main, Jul 5 2023, 19:22:19) [GCC 11.2.0]", "command_line_arguments": "/home/abdelrhman/anaconda3/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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706883051" }, "total": 320.6040768290004, "count": 1, "self": 0.31469547800134023, "children": { "run_training.setup": { "total": 0.030145511999762675, "count": 1, "self": 0.030145511999762675 }, "TrainerController.start_learning": { "total": 320.2592358389993, "count": 1, "self": 0.4511803521454567, "children": { "TrainerController._reset_env": { "total": 4.142564825999216, "count": 1, "self": 4.142564825999216 }, "TrainerController.advance": { "total": 315.59809550985483, "count": 18202, "self": 0.23089917895413237, "children": { "env_step": { "total": 315.3671963309007, "count": 18202, "self": 236.26508758583714, "children": { "SubprocessEnvManager._take_step": { "total": 78.84615986599965, "count": 18202, "self": 1.2002429959911751, "children": { "TorchPolicy.evaluate": { "total": 77.64591687000848, "count": 18202, "self": 77.64591687000848 } } }, "workers": { "total": 0.25594887906390795, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 319.6698174879157, "count": 18202, "is_parallel": true, "self": 146.88145845492636, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0668945099996563, "count": 1, "is_parallel": true, "self": 0.06575302299916075, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011414870004955446, "count": 10, "is_parallel": true, "self": 0.0011414870004955446 } } }, "UnityEnvironment.step": { "total": 0.024550355999963358, "count": 1, "is_parallel": true, "self": 0.0004424759999892558, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024819600002956577, "count": 1, "is_parallel": true, "self": 0.00024819600002956577 }, "communicator.exchange": { "total": 0.022887166000145953, "count": 1, "is_parallel": true, "self": 0.022887166000145953 }, "steps_from_proto": { "total": 0.0009725179997985833, "count": 1, "is_parallel": true, "self": 0.00020259899974917062, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007699190000494127, "count": 10, "is_parallel": true, "self": 0.0007699190000494127 } } } } } } }, "UnityEnvironment.step": { "total": 172.78835903298932, "count": 18201, "is_parallel": true, "self": 8.69084218597527, "children": { "UnityEnvironment._generate_step_input": { "total": 4.482548058999782, "count": 18201, "is_parallel": true, "self": 4.482548058999782 }, "communicator.exchange": { "total": 134.81018395204592, "count": 18201, "is_parallel": true, "self": 134.81018395204592 }, "steps_from_proto": { "total": 24.80478483596835, "count": 18201, "is_parallel": true, "self": 4.505947047925474, "children": { "_process_rank_one_or_two_observation": { "total": 20.298837788042874, "count": 182010, "is_parallel": true, "self": 20.298837788042874 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018042099964077352, "count": 1, "self": 0.00018042099964077352, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 314.63550874305747, "count": 200341, "is_parallel": true, "self": 3.3235108043973014, "children": { "process_trajectory": { "total": 176.79833742265964, "count": 200341, "is_parallel": true, "self": 176.3771558976605, "children": { "RLTrainer._checkpoint": { "total": 0.42118152499915595, "count": 4, "is_parallel": true, "self": 0.42118152499915595 } } }, "_update_policy": { "total": 134.51366051600053, "count": 90, "is_parallel": true, "self": 33.53424243702193, "children": { "TorchPPOOptimizer.update": { "total": 100.9794180789786, "count": 4587, "is_parallel": true, "self": 100.9794180789786 } } } } } } } } }, "TrainerController._save_models": { "total": 0.06721473000015976, "count": 1, "self": 0.0008340240001416532, "children": { "RLTrainer._checkpoint": { "total": 0.06638070600001811, "count": 1, "self": 0.06638070600001811 } } } } } } }