{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9156668186187744, "min": 0.9156668186187744, "max": 2.8620622158050537, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8752.859375, "min": 8752.859375, "max": 29310.37890625, "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": 12.55387020111084, "min": 0.3421741724014282, "max": 12.55387020111084, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2448.004638671875, "min": 66.38179016113281, "max": 2546.33544921875, "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": 0.06973605318675183, "min": 0.06340181107082696, "max": 0.07342574787988126, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2789442127470073, "min": 0.26361911845913927, "max": 0.3653856964591279, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22378668999847243, "min": 0.1282015477807042, "max": 0.2832070429097204, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8951467599938897, "min": 0.5128061911228168, "max": 1.2878264340699888, "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": 24.272727272727273, "min": 3.590909090909091, "max": 24.8, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1068.0, "min": 158.0, "max": 1364.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.272727272727273, "min": 3.590909090909091, "max": 24.8, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1068.0, "min": 158.0, "max": 1364.0, "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": "1702473201", "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": "1702473722" }, "total": 521.2678356470001, "count": 1, "self": 0.6078739900001437, "children": { "run_training.setup": { "total": 0.08978679000000511, "count": 1, "self": 0.08978679000000511 }, "TrainerController.start_learning": { "total": 520.570174867, "count": 1, "self": 0.6624922780041516, "children": { "TrainerController._reset_env": { "total": 3.988737224000033, "count": 1, "self": 3.988737224000033 }, "TrainerController.advance": { "total": 515.8240471469958, "count": 18200, "self": 0.3188891479940139, "children": { "env_step": { "total": 515.5051579990018, "count": 18200, "self": 352.88111918099884, "children": { "SubprocessEnvManager._take_step": { "total": 162.28849070600552, "count": 18200, "self": 1.6603209550119686, "children": { "TorchPolicy.evaluate": { "total": 160.62816975099355, "count": 18200, "self": 160.62816975099355 } } }, "workers": { "total": 0.3355481119974115, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 519.1207598600031, "count": 18200, "is_parallel": true, "self": 253.65377506400017, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0050590569999826585, "count": 1, "is_parallel": true, "self": 0.0028161570000406755, "children": { "_process_rank_one_or_two_observation": { "total": 0.002242899999941983, "count": 10, "is_parallel": true, "self": 0.002242899999941983 } } }, "UnityEnvironment.step": { "total": 0.04091700200001469, "count": 1, "is_parallel": true, "self": 0.0006359720000546076, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000339795000002141, "count": 1, "is_parallel": true, "self": 0.000339795000002141 }, "communicator.exchange": { "total": 0.03467620999998644, "count": 1, "is_parallel": true, "self": 0.03467620999998644 }, "steps_from_proto": { "total": 0.0052650249999715015, "count": 1, "is_parallel": true, "self": 0.0004585589999805961, "children": { "_process_rank_one_or_two_observation": { "total": 0.004806465999990905, "count": 10, "is_parallel": true, "self": 0.004806465999990905 } } } } } } }, "UnityEnvironment.step": { "total": 265.4669847960029, "count": 18199, "is_parallel": true, "self": 11.59893576299686, "children": { "UnityEnvironment._generate_step_input": { "total": 6.073296050007514, "count": 18199, "is_parallel": true, "self": 6.073296050007514 }, "communicator.exchange": { "total": 209.10708031499672, "count": 18199, "is_parallel": true, "self": 209.10708031499672 }, "steps_from_proto": { "total": 38.687672668001824, "count": 18199, "is_parallel": true, "self": 7.4655959949925546, "children": { "_process_rank_one_or_two_observation": { "total": 31.22207667300927, "count": 181990, "is_parallel": true, "self": 31.22207667300927 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012391699999625416, "count": 1, "self": 0.00012391699999625416, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 511.21731644797205, "count": 550587, "is_parallel": true, "self": 12.292465783953674, "children": { "process_trajectory": { "total": 290.0372584690186, "count": 550587, "is_parallel": true, "self": 289.4959819490186, "children": { "RLTrainer._checkpoint": { "total": 0.5412765199999967, "count": 4, "is_parallel": true, "self": 0.5412765199999967 } } }, "_update_policy": { "total": 208.8875921949998, "count": 90, "is_parallel": true, "self": 66.15059266899834, "children": { "TorchPPOOptimizer.update": { "total": 142.73699952600145, "count": 4587, "is_parallel": true, "self": 142.73699952600145 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09477430100002948, "count": 1, "self": 0.001688990000047852, "children": { "RLTrainer._checkpoint": { "total": 0.09308531099998163, "count": 1, "self": 0.09308531099998163 } } } } } } }