{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9865577220916748, "min": 0.9813318252563477, "max": 2.8729496002197266, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9419.6533203125, "min": 9419.6533203125, "max": 29453.478515625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.973301887512207, "min": 0.2207619845867157, "max": 12.973301887512207, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2529.7939453125, "min": 42.827823638916016, "max": 2622.993896484375, "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": 0.06552032656733953, "min": 0.061822530513175065, "max": 0.07568955009794046, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2620813062693581, "min": 0.26133882877868875, "max": 0.37844775048970225, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18807489724428045, "min": 0.10337519467529822, "max": 0.27367406674459865, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7522995889771218, "min": 0.4135007787011929, "max": 1.3368275358396418, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.34090909090909, "min": 3.2045454545454546, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1115.0, "min": 141.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.34090909090909, "min": 3.2045454545454546, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1115.0, "min": 141.0, "max": 1402.0, "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": "1717189552", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717189987" }, "total": 435.508706341, "count": 1, "self": 0.43685978399997794, "children": { "run_training.setup": { "total": 0.06344576200001484, "count": 1, "self": 0.06344576200001484 }, "TrainerController.start_learning": { "total": 435.008400795, "count": 1, "self": 0.516328240009841, "children": { "TrainerController._reset_env": { "total": 2.998632901999997, "count": 1, "self": 2.998632901999997 }, "TrainerController.advance": { "total": 431.4062176289902, "count": 18201, "self": 0.2518533759903221, "children": { "env_step": { "total": 431.15436425299987, "count": 18201, "self": 278.52811762499255, "children": { "SubprocessEnvManager._take_step": { "total": 152.36243365601052, "count": 18201, "self": 1.4004995650174124, "children": { "TorchPolicy.evaluate": { "total": 150.9619340909931, "count": 18201, "self": 150.9619340909931 } } }, "workers": { "total": 0.2638129719967992, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 433.9324020530033, "count": 18201, "is_parallel": true, "self": 221.0878876360062, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005471679999971002, "count": 1, "is_parallel": true, "self": 0.003958641999986412, "children": { "_process_rank_one_or_two_observation": { "total": 0.00151303799998459, "count": 10, "is_parallel": true, "self": 0.00151303799998459 } } }, "UnityEnvironment.step": { "total": 0.03565433200003554, "count": 1, "is_parallel": true, "self": 0.000673025000025973, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042166600002246923, "count": 1, "is_parallel": true, "self": 0.00042166600002246923 }, "communicator.exchange": { "total": 0.03259452300000021, "count": 1, "is_parallel": true, "self": 0.03259452300000021 }, "steps_from_proto": { "total": 0.0019651179999868873, "count": 1, "is_parallel": true, "self": 0.0004045309999582969, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015605870000285904, "count": 10, "is_parallel": true, "self": 0.0015605870000285904 } } } } } } }, "UnityEnvironment.step": { "total": 212.84451441699707, "count": 18200, "is_parallel": true, "self": 9.82753540098696, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2040644379990795, "count": 18200, "is_parallel": true, "self": 5.2040644379990795 }, "communicator.exchange": { "total": 165.9977262220046, "count": 18200, "is_parallel": true, "self": 165.9977262220046 }, "steps_from_proto": { "total": 31.815188356006445, "count": 18200, "is_parallel": true, "self": 5.844504696031947, "children": { "_process_rank_one_or_two_observation": { "total": 25.970683659974497, "count": 182000, "is_parallel": true, "self": 25.970683659974497 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012746499999138905, "count": 1, "self": 0.00012746499999138905, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 426.1604688499305, "count": 642370, "is_parallel": true, "self": 13.271612463939562, "children": { "process_trajectory": { "total": 234.13920507699055, "count": 642370, "is_parallel": true, "self": 233.46849316099048, "children": { "RLTrainer._checkpoint": { "total": 0.670711916000073, "count": 4, "is_parallel": true, "self": 0.670711916000073 } } }, "_update_policy": { "total": 178.7496513090004, "count": 90, "is_parallel": true, "self": 57.893478244998676, "children": { "TorchPPOOptimizer.update": { "total": 120.85617306400172, "count": 4587, "is_parallel": true, "self": 120.85617306400172 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0870945589999792, "count": 1, "self": 0.0009050620000152776, "children": { "RLTrainer._checkpoint": { "total": 0.08618949699996392, "count": 1, "self": 0.08618949699996392 } } } } } } }