{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.846041202545166, "min": 2.846041202545166, "max": 2.846041202545166, "count": 1 }, "SnowballTarget.Policy.Entropy.sum": { "value": 29240.228515625, "min": 29240.228515625, "max": 29240.228515625, "count": 1 }, "SnowballTarget.Step.mean": { "value": 9952.0, "min": 9952.0, "max": 9952.0, "count": 1 }, "SnowballTarget.Step.sum": { "value": 9952.0, "min": 9952.0, "max": 9952.0, "count": 1 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4401145875453949, "min": 0.4401145875453949, "max": 0.4401145875453949, "count": 1 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 85.38223266601562, "min": 85.38223266601562, "max": 85.38223266601562, "count": 1 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 1 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 8756.0, "count": 1 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06452677243357009, "min": 0.06452677243357009, "max": 0.06452677243357009, "count": 1 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25810708973428037, "min": 0.25810708973428037, "max": 0.25810708973428037, "count": 1 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14674226341508878, "min": 0.14674226341508878, "max": 0.14674226341508878, "count": 1 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5869690536603551, "min": 0.5869690536603551, "max": 0.5869690536603551, "count": 1 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00036704005412000005, "min": 0.00036704005412000005, "max": 0.00036704005412000005, "count": 1 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0014681602164800002, "min": 0.0014681602164800002, "max": 0.0014681602164800002, "count": 1 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.19175999999999999, "min": 0.19175999999999999, "max": 0.19175999999999999, "count": 1 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.7670399999999999, "min": 0.7670399999999999, "max": 0.7670399999999999, "count": 1 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0022994120000000002, "min": 0.0022994120000000002, "max": 0.0022994120000000002, "count": 1 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.009197648000000001, "min": 0.009197648000000001, "max": 0.009197648000000001, "count": 1 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 4.590909090909091, "min": 4.590909090909091, "max": 4.590909090909091, "count": 1 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 202.0, "min": 202.0, "max": 202.0, "count": 1 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 4.590909090909091, "min": 4.590909090909091, "max": 4.590909090909091, "count": 1 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 202.0, "min": 202.0, "max": 202.0, "count": 1 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685595019", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1685595049" }, "total": 29.61313375900005, "count": 1, "self": 0.4357276060000004, "children": { "run_training.setup": { "total": 0.046593137000002116, "count": 1, "self": 0.046593137000002116 }, "TrainerController.start_learning": { "total": 29.130813016000047, "count": 1, "self": 0.045488033998992705, "children": { "TrainerController._reset_env": { "total": 3.833461424999996, "count": 1, "self": 3.833461424999996 }, "TrainerController.advance": { "total": 25.070121971001015, "count": 935, "self": 0.013724680999644079, "children": { "env_step": { "total": 25.05639729000137, "count": 935, "self": 18.975259537001534, "children": { "SubprocessEnvManager._take_step": { "total": 6.067545177999875, "count": 935, "self": 0.08060151100005442, "children": { "TorchPolicy.evaluate": { "total": 5.986943666999821, "count": 935, "self": 5.986943666999821 } } }, "workers": { "total": 0.013592574999961471, "count": 935, "self": 0.0, "children": { "worker_root": { "total": 28.907935369997404, "count": 935, "is_parallel": true, "self": 16.37485035099587, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005764760999966256, "count": 1, "is_parallel": true, "self": 0.004150438000010581, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016143229999556752, "count": 10, "is_parallel": true, "self": 0.0016143229999556752 } } }, "UnityEnvironment.step": { "total": 0.034132045999967886, "count": 1, "is_parallel": true, "self": 0.0005997170000000551, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003979109999932007, "count": 1, "is_parallel": true, "self": 0.0003979109999932007 }, "communicator.exchange": { "total": 0.031064049999997678, "count": 1, "is_parallel": true, "self": 0.031064049999997678 }, "steps_from_proto": { "total": 0.002070367999976952, "count": 1, "is_parallel": true, "self": 0.00037831000003052395, "children": { "_process_rank_one_or_two_observation": { "total": 0.001692057999946428, "count": 10, "is_parallel": true, "self": 0.001692057999946428 } } } } } } }, "UnityEnvironment.step": { "total": 12.533085019001533, "count": 934, "is_parallel": true, "self": 0.5124389069983408, "children": { "UnityEnvironment._generate_step_input": { "total": 0.26226628900121796, "count": 934, "is_parallel": true, "self": 0.26226628900121796 }, "communicator.exchange": { "total": 10.02718637199979, "count": 934, "is_parallel": true, "self": 10.02718637199979 }, "steps_from_proto": { "total": 1.7311934510021842, "count": 934, "is_parallel": true, "self": 0.32734452901064515, "children": { "_process_rank_one_or_two_observation": { "total": 1.403848921991539, "count": 9340, "is_parallel": true, "self": 1.403848921991539 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021319799998309463, "count": 1, "self": 0.00021319799998309463, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 24.89610477199807, "count": 23424, "is_parallel": true, "self": 0.5172941500018737, "children": { "process_trajectory": { "total": 13.50148267199603, "count": 23424, "is_parallel": true, "self": 13.50148267199603 }, "_update_policy": { "total": 10.877327950000165, "count": 4, "is_parallel": true, "self": 4.558087949000367, "children": { "TorchPPOOptimizer.update": { "total": 6.319240000999798, "count": 268, "is_parallel": true, "self": 6.319240000999798 } } } } } } } } }, "TrainerController._save_models": { "total": 0.18152838800006066, "count": 1, "self": 0.0011862840000276265, "children": { "RLTrainer._checkpoint": { "total": 0.18034210400003303, "count": 1, "self": 0.18034210400003303 } } } } } } }