{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.0494461059570312, "min": 2.0494461059570312, "max": 2.8376970291137695, "count": 4 }, "SnowballTarget.Policy.Entropy.sum": { "value": 102214.078125, "min": 102214.078125, "max": 143368.96875, "count": 4 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 49936.0, "max": 199984.0, "count": 4 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 49936.0, "max": 199984.0, "count": 4 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 4.454984664916992, "min": 0.4939333498477936, "max": 4.454984664916992, "count": 4 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 4423.7998046875, "min": 489.98187255859375, "max": 4423.7998046875, "count": 4 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 4 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 50347.0, "min": 48158.0, "max": 50347.0, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 12.714876033057852, "min": 4.1115702479338845, "max": 12.714876033057852, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 3077.0, "min": 995.0, "max": 3077.0, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 12.587727238324064, "min": 4.0704545757987285, "max": 12.587727238324064, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 3046.229991674423, "min": 985.0500073432922, "max": 3046.229991674423, "count": 4 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.03343466497920518, "min": 0.03343466497920518, "max": 0.0346642195055167, "count": 4 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.1671733248960259, "min": 0.1386568780220668, "max": 0.171164439183081, "count": 4 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.28115746842726824, "min": 0.13410471987481865, "max": 0.28115746842726824, "count": 4 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.4057873421363412, "min": 0.5364188794992746, "max": 1.4057873421363412, "count": 4 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.3201688932800005e-05, "min": 3.3201688932800005e-05, "max": 0.000260466013178, "count": 4 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00016600844466400003, "min": 0.00016600844466400003, "max": 0.001041864052712, "count": 4 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1110672, "min": 0.1110672, "max": 0.18682200000000004, "count": 4 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.555336, "min": 0.555336, "max": 0.8164319999999998, "count": 4 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.422928e-05, "min": 6.422928e-05, "max": 0.00043542779999999995, "count": 4 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00032114640000000005, "min": 0.00032114640000000005, "max": 0.0017417111999999998, "count": 4 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1725290324", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725290819" }, "total": 494.97384916600004, "count": 1, "self": 0.7998216519999914, "children": { "run_training.setup": { "total": 0.05353985799979455, "count": 1, "self": 0.05353985799979455 }, "TrainerController.start_learning": { "total": 494.12048765600025, "count": 1, "self": 0.7176941629882094, "children": { "TrainerController._reset_env": { "total": 2.1921648860000005, "count": 1, "self": 2.1921648860000005 }, "TrainerController.advance": { "total": 491.0767997340122, "count": 18209, "self": 0.3101109120086676, "children": { "env_step": { "total": 490.7666888220035, "count": 18209, "self": 310.3830554779654, "children": { "SubprocessEnvManager._take_step": { "total": 180.06244985901503, "count": 18209, "self": 1.635316708000346, "children": { "TorchPolicy.evaluate": { "total": 178.4271331510147, "count": 18209, "self": 178.4271331510147 } } }, "workers": { "total": 0.32118348502308436, "count": 18209, "self": 0.0, "children": { "worker_root": { "total": 492.701129123991, "count": 18209, "is_parallel": true, "self": 251.69742168399102, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022424290000344627, "count": 1, "is_parallel": true, "self": 0.00067107200038663, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015713569996478327, "count": 10, "is_parallel": true, "self": 0.0015713569996478327 } } }, "UnityEnvironment.step": { "total": 0.03687510000008842, "count": 1, "is_parallel": true, "self": 0.0005897319997529848, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037793000001329347, "count": 1, "is_parallel": true, "self": 0.00037793000001329347 }, "communicator.exchange": { "total": 0.03384489300015048, "count": 1, "is_parallel": true, "self": 0.03384489300015048 }, "steps_from_proto": { "total": 0.002062545000171667, "count": 1, "is_parallel": true, "self": 0.0003988020002907433, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016637429998809239, "count": 10, "is_parallel": true, "self": 0.0016637429998809239 } } } } } } }, "UnityEnvironment.step": { "total": 241.00370743999997, "count": 18208, "is_parallel": true, "self": 10.881220365014315, "children": { "UnityEnvironment._generate_step_input": { "total": 5.906595711994896, "count": 18208, "is_parallel": true, "self": 5.906595711994896 }, "communicator.exchange": { "total": 187.45577105800385, "count": 18208, "is_parallel": true, "self": 187.45577105800385 }, "steps_from_proto": { "total": 36.76012030498691, "count": 18208, "is_parallel": true, "self": 7.075542106988223, "children": { "_process_rank_one_or_two_observation": { "total": 29.68457819799869, "count": 182080, "is_parallel": true, "self": 29.68457819799869 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019802699989668326, "count": 1, "self": 0.00019802699989668326, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 481.49783629407375, "count": 1047126, "is_parallel": true, "self": 23.10743318343134, "children": { "process_trajectory": { "total": 363.7354456546425, "count": 1047126, "is_parallel": true, "self": 362.5283601466426, "children": { "RLTrainer._checkpoint": { "total": 1.2070855079998637, "count": 4, "is_parallel": true, "self": 1.2070855079998637 } } }, "_update_policy": { "total": 94.65495745599992, "count": 19, "is_parallel": true, "self": 54.08066875000077, "children": { "TorchPPOOptimizer.update": { "total": 40.57428870599915, "count": 1155, "is_parallel": true, "self": 40.57428870599915 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13363084599996, "count": 1, "self": 0.0011252919998696598, "children": { "RLTrainer._checkpoint": { "total": 0.13250555400009034, "count": 1, "self": 0.13250555400009034 } } } } } } }