{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5601517558097839, "min": 0.5137851238250732, "max": 2.8594589233398438, "count": 90 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5785.8076171875, "min": 4877.3623046875, "max": 29315.173828125, "count": 90 }, "SnowballTarget.Step.mean": { "value": 899992.0, "min": 9952.0, "max": 899992.0, "count": 90 }, "SnowballTarget.Step.sum": { "value": 899992.0, "min": 9952.0, "max": 899992.0, "count": 90 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.026276588439941, "min": 0.3239937126636505, "max": 14.155049324035645, "count": 90 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2875.38671875, "min": 62.85477828979492, "max": 2901.78515625, "count": 90 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 90 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 90 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06920327269472182, "min": 0.05802497048445694, "max": 0.07891666372169685, "count": 90 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3460163634736091, "min": 0.23209988193782777, "max": 0.3945833186084843, "count": 90 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16916274320261154, "min": 0.10606509628340455, "max": 0.2839184609698314, "count": 90 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8458137160130577, "min": 0.4242603851336182, "max": 1.4195923048491572, "count": 90 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.5627661457777764e-06, "min": 1.5627661457777764e-06, "max": 0.0002981960006013333, "count": 90 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 7.813830728888882e-06, "min": 7.813830728888882e-06, "max": 0.0014744800085066665, "count": 90 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10052088888888888, "min": 0.10052088888888888, "max": 0.19939866666666672, "count": 90 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5026044444444444, "min": 0.40648355555555554, "max": 0.9914933333333332, "count": 90 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.599235555555554e-05, "min": 3.599235555555554e-05, "max": 0.004969993466666666, "count": 90 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0001799617777777777, "min": 0.0001799617777777777, "max": 0.02457551733333333, "count": 90 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.490909090909092, "min": 3.227272727272727, "max": 28.022727272727273, "count": 90 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1512.0, "min": 142.0, "max": 1536.0, "count": 90 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.490909090909092, "min": 3.227272727272727, "max": 28.022727272727273, "count": 90 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1512.0, "min": 142.0, "max": 1536.0, "count": 90 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 90 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 90 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708449722", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/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": "1708451846" }, "total": 2124.288374626, "count": 1, "self": 0.48498972599963963, "children": { "run_training.setup": { "total": 0.05082832000005055, "count": 1, "self": 0.05082832000005055 }, "TrainerController.start_learning": { "total": 2123.75255658, "count": 1, "self": 2.9217817370126795, "children": { "TrainerController._reset_env": { "total": 3.5906232009999712, "count": 1, "self": 3.5906232009999712 }, "TrainerController.advance": { "total": 2117.142485936987, "count": 81884, "self": 1.4324566069690263, "children": { "env_step": { "total": 2115.710029330018, "count": 81884, "self": 1378.4128894129394, "children": { "SubprocessEnvManager._take_step": { "total": 735.8304491690193, "count": 81884, "self": 7.095135940995192, "children": { "TorchPolicy.evaluate": { "total": 728.7353132280241, "count": 81884, "self": 728.7353132280241 } } }, "workers": { "total": 1.466690748059591, "count": 81884, "self": 0.0, "children": { "worker_root": { "total": 2118.054490967004, "count": 81884, "is_parallel": true, "self": 1038.412207756007, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005791361999968103, "count": 1, "is_parallel": true, "self": 0.003882118999740669, "children": { "_process_rank_one_or_two_observation": { "total": 0.001909243000227434, "count": 10, "is_parallel": true, "self": 0.001909243000227434 } } }, "UnityEnvironment.step": { "total": 0.06741638900007274, "count": 1, "is_parallel": true, "self": 0.0021878979998746217, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046122600008402515, "count": 1, "is_parallel": true, "self": 0.00046122600008402515 }, "communicator.exchange": { "total": 0.06259762700005922, "count": 1, "is_parallel": true, "self": 0.06259762700005922 }, "steps_from_proto": { "total": 0.0021696380000548743, "count": 1, "is_parallel": true, "self": 0.0005997080002089206, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015699299998459537, "count": 10, "is_parallel": true, "self": 0.0015699299998459537 } } } } } } }, "UnityEnvironment.step": { "total": 1079.6422832109968, "count": 81883, "is_parallel": true, "self": 51.19035017696319, "children": { "UnityEnvironment._generate_step_input": { "total": 26.557305570040057, "count": 81883, "is_parallel": true, "self": 26.557305570040057 }, "communicator.exchange": { "total": 835.6340489199785, "count": 81883, "is_parallel": true, "self": 835.6340489199785 }, "steps_from_proto": { "total": 166.26057854401517, "count": 81883, "is_parallel": true, "self": 31.60611159295877, "children": { "_process_rank_one_or_two_observation": { "total": 134.6544669510564, "count": 818830, "is_parallel": true, "self": 134.6544669510564 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002615799999148294, "count": 1, "self": 0.0002615799999148294, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2090.1667035965816, "count": 3209209, "is_parallel": true, "self": 69.47002577047579, "children": { "process_trajectory": { "total": 1152.89243171211, "count": 3209209, "is_parallel": true, "self": 1149.7660388131098, "children": { "RLTrainer._checkpoint": { "total": 3.126392899000166, "count": 18, "is_parallel": true, "self": 3.126392899000166 } } }, "_update_policy": { "total": 867.8042461139958, "count": 409, "is_parallel": true, "self": 242.18361937897726, "children": { "TorchPPOOptimizer.update": { "total": 625.6206267350185, "count": 20856, "is_parallel": true, "self": 625.6206267350185 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09740412500013917, "count": 1, "self": 0.0010115459999724408, "children": { "RLTrainer._checkpoint": { "total": 0.09639257900016673, "count": 1, "self": 0.09639257900016673 } } } } } } }