{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7013018727302551, "min": 0.6640027165412903, "max": 0.8622682094573975, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6680.6015625, "min": 6339.89794921875, "max": 8294.6728515625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 399984.0, "min": 209952.0, "max": 399984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 399984.0, "min": 209952.0, "max": 399984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.379910469055176, "min": 12.89579963684082, "max": 13.408547401428223, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2609.08251953125, "min": 2372.8271484375, "max": 2735.34375, "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": 0.0686802695690858, "min": 0.06430996767263494, "max": 0.0772170364093743, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2747210782763432, "min": 0.2572398706905398, "max": 0.3721021125777898, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17806019392960212, "min": 0.1707822937591403, "max": 0.2220527931171305, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7122407757184085, "min": 0.6831291750365612, "max": 1.1102639655856525, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.561098812999997e-06, "min": 3.561098812999997e-06, "max": 0.000145461051513, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.4244395251999988e-05, "min": 1.4244395251999988e-05, "max": 0.0006571802809399999, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.101187, "min": 0.101187, "max": 0.148487, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.404748, "min": 0.404748, "max": 0.71906, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.923129999999995e-05, "min": 6.923129999999995e-05, "max": 0.0024295013000000007, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0002769251999999998, "min": 0.0002769251999999998, "max": 0.010981094, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.34090909090909, "min": 25.327272727272728, "max": 26.522727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1159.0, "min": 1120.0, "max": 1446.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.34090909090909, "min": 25.327272727272728, "max": 26.522727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1159.0, "min": 1120.0, "max": 1446.0, "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": "1676486508", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/home/jonatan/PycharmProjects/HuggingfaceDeepRLCourse/Unit5/venv/bin/mlagents-learn ./content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.23.5", "end_time_seconds": "1676486828" }, "total": 319.7264541609911, "count": 1, "self": 0.3750912419054657, "children": { "run_training.setup": { "total": 0.01992227102164179, "count": 1, "self": 0.01992227102164179 }, "TrainerController.start_learning": { "total": 319.331440648064, "count": 1, "self": 0.44656072894576937, "children": { "TrainerController._reset_env": { "total": 2.602945677936077, "count": 1, "self": 2.602945677936077 }, "TrainerController.advance": { "total": 316.15822794416454, "count": 18140, "self": 0.20747006044257432, "children": { "env_step": { "total": 315.95075788372196, "count": 18140, "self": 215.02938846347388, "children": { "SubprocessEnvManager._take_step": { "total": 100.67914684314746, "count": 18140, "self": 1.143365952768363, "children": { "TorchPolicy.evaluate": { "total": 99.5357808903791, "count": 18140, "self": 24.05113153764978, "children": { "TorchPolicy.sample_actions": { "total": 75.48464935272932, "count": 18140, "self": 75.48464935272932 } } } } }, "workers": { "total": 0.24222257710061967, "count": 18140, "self": 0.0, "children": { "worker_root": { "total": 318.66177946177777, "count": 18140, "is_parallel": true, "self": 163.58133103558794, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014973619254305959, "count": 1, "is_parallel": true, "self": 0.00041328067891299725, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010840812465175986, "count": 10, "is_parallel": true, "self": 0.0010840812465175986 } } }, "UnityEnvironment.step": { "total": 0.022471531061455607, "count": 1, "is_parallel": true, "self": 0.00029101502150297165, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020799902267754078, "count": 1, "is_parallel": true, "self": 0.00020799902267754078 }, "communicator.exchange": { "total": 0.021059047081507742, "count": 1, "is_parallel": true, "self": 0.021059047081507742 }, "steps_from_proto": { "total": 0.0009134699357673526, "count": 1, "is_parallel": true, "self": 0.0002164661418646574, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006970037939026952, "count": 10, "is_parallel": true, "self": 0.0006970037939026952 } } } } } } }, "UnityEnvironment.step": { "total": 155.08044842618983, "count": 18139, "is_parallel": true, "self": 7.599670621799305, "children": { "UnityEnvironment._generate_step_input": { "total": 4.053588181035593, "count": 18139, "is_parallel": true, "self": 4.053588181035593 }, "communicator.exchange": { "total": 123.36690755712334, "count": 18139, "is_parallel": true, "self": 123.36690755712334 }, "steps_from_proto": { "total": 20.060282066231593, "count": 18139, "is_parallel": true, "self": 4.2335486222291365, "children": { "_process_rank_one_or_two_observation": { "total": 15.826733444002457, "count": 181390, "is_parallel": true, "self": 15.826733444002457 } } } } } } } } } } } } }, "trainer_threads": { "total": 7.423898205161095e-05, "count": 1, "self": 7.423898205161095e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 314.5764184364816, "count": 361499, "is_parallel": true, "self": 4.800364643684588, "children": { "process_trajectory": { "total": 175.4521761490032, "count": 361499, "is_parallel": true, "self": 174.722319738823, "children": { "RLTrainer._checkpoint": { "total": 0.7298564101802185, "count": 4, "is_parallel": true, "self": 0.7298564101802185 } } }, "_update_policy": { "total": 134.32387764379382, "count": 90, "is_parallel": true, "self": 39.981511781108566, "children": { "TorchPPOOptimizer.update": { "total": 94.34236586268526, "count": 4587, "is_parallel": true, "self": 94.34236586268526 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1236320580355823, "count": 1, "self": 0.000865268986672163, "children": { "RLTrainer._checkpoint": { "total": 0.12276678904891014, "count": 1, "self": 0.12276678904891014 } } } } } } }