{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.769853115081787, "min": 2.769853115081787, "max": 2.874423027038574, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 28487.939453125, "min": 28487.939453125, "max": 29500.203125, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.4930202960968018, "min": 0.508807361125946, "max": 1.4930202960968018, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 306.06915283203125, "min": 98.70863342285156, "max": 306.06915283203125, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07282637385806975, "min": 0.06170915552766197, "max": 0.07282637385806975, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.36413186929034874, "min": 0.24683662211064789, "max": 0.36413186929034874, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2201046543378456, "min": 0.1344224326951685, "max": 0.2201046543378456, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.100523271689228, "min": 0.537689730780674, "max": 1.100523271689228, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032007656e-05, "min": 7.032007656e-05, "max": 0.00021882002706000002, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003516003828, "min": 0.0003516003828, "max": 0.0008752801082400001, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12344000000000002, "min": 0.12344000000000002, "max": 0.17294, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6172000000000001, "min": 0.6172000000000001, "max": 0.69176, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011796560000000003, "min": 0.0011796560000000003, "max": 0.003649706, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005898280000000001, "min": 0.005898280000000001, "max": 0.014598824, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 5.8, "min": 3.840909090909091, "max": 5.8, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 319.0, "min": 169.0, "max": 319.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 5.8, "min": 3.840909090909091, "max": 5.8, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 319.0, "min": 169.0, "max": 319.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739102314", "python_version": "3.10.12 (main, Jan 20 2025, 19:07:01) [GCC 13.3.0]", "command_line_arguments": "/home/fabiofava98/Desktop_Ubuntu/AI/HuggingFace_RL_Course/venv_unit5/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739102338" }, "total": 23.516157119000127, "count": 1, "self": 0.21971874900009425, "children": { "run_training.setup": { "total": 0.013961511999696086, "count": 1, "self": 0.013961511999696086 }, "TrainerController.start_learning": { "total": 23.282476858000337, "count": 1, "self": 0.12490293202790781, "children": { "TrainerController._reset_env": { "total": 1.1738431149997268, "count": 1, "self": 1.1738431149997268 }, "TrainerController.advance": { "total": 21.91450159597207, "count": 1869, "self": 0.016905132973988657, "children": { "env_step": { "total": 21.89759646299808, "count": 1869, "self": 14.34742218300562, "children": { "SubprocessEnvManager._take_step": { "total": 7.534812117000911, "count": 1869, "self": 0.07916982200185885, "children": { "TorchPolicy.evaluate": { "total": 7.455642294999052, "count": 1869, "self": 7.455642294999052 } } }, "workers": { "total": 0.015362162991550576, "count": 1869, "self": 0.0, "children": { "worker_root": { "total": 23.07157594999262, "count": 1869, "is_parallel": true, "self": 13.539386846980051, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012914600001749932, "count": 1, "is_parallel": true, "self": 0.0004209560020171921, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008705039981578011, "count": 10, "is_parallel": true, "self": 0.0008705039981578011 } } }, "UnityEnvironment.step": { "total": 0.015365346999715257, "count": 1, "is_parallel": true, "self": 0.00019276099919807166, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018781300059345085, "count": 1, "is_parallel": true, "self": 0.00018781300059345085 }, "communicator.exchange": { "total": 0.014154526000311307, "count": 1, "is_parallel": true, "self": 0.014154526000311307 }, "steps_from_proto": { "total": 0.0008302469996124273, "count": 1, "is_parallel": true, "self": 0.00019043499833060196, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006398120012818254, "count": 10, "is_parallel": true, "self": 0.0006398120012818254 } } } } } } }, "UnityEnvironment.step": { "total": 9.53218910301257, "count": 1868, "is_parallel": true, "self": 0.35752987602063513, "children": { "UnityEnvironment._generate_step_input": { "total": 0.2274653499962369, "count": 1868, "is_parallel": true, "self": 0.2274653499962369 }, "communicator.exchange": { "total": 7.644632489990727, "count": 1868, "is_parallel": true, "self": 7.644632489990727 }, "steps_from_proto": { "total": 1.302561387004971, "count": 1868, "is_parallel": true, "self": 0.2959898670333132, "children": { "_process_rank_one_or_two_observation": { "total": 1.0065715199716578, "count": 18680, "is_parallel": true, "self": 1.0065715199716578 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002494890004527406, "count": 1, "self": 0.0002494890004527406, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 21.93668929206342, "count": 14378, "is_parallel": true, "self": 0.25066437101213523, "children": { "process_trajectory": { "total": 11.99945008305258, "count": 14378, "is_parallel": true, "self": 11.99945008305258 }, "_update_policy": { "total": 9.686574837998705, "count": 9, "is_parallel": true, "self": 3.1305042360045263, "children": { "TorchPPOOptimizer.update": { "total": 6.556070601994179, "count": 456, "is_parallel": true, "self": 6.556070601994179 } } } } } } } } }, "TrainerController._save_models": { "total": 0.06897972600017965, "count": 1, "self": 0.0009669300006862613, "children": { "RLTrainer._checkpoint": { "total": 0.06801279599949339, "count": 1, "self": 0.06801279599949339 } } } } } } }