{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8043200373649597, "min": 0.8043200373649597, "max": 2.7780442237854004, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 20004.244140625, "min": 20004.244140625, "max": 71140.15625, "count": 10 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 24968.0, "max": 249944.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 24968.0, "max": 249944.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.918333053588867, "min": 1.5000251531600952, "max": 12.918333053588867, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 6407.4931640625, "min": 744.012451171875, "max": 6500.25, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 24079.0, "min": 24079.0, "max": 26268.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07106770183039733, "min": 0.06466161525183484, "max": 0.07106770183039733, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.7817447201343706, "min": 0.7203032469906783, "max": 0.8125237732641408, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.4287600515280815, "min": 0.37541913263061466, "max": 0.6702050964037577, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 4.716360566808897, "min": 4.129610458936761, "max": 8.042461156845093, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.4976095004800003e-05, "min": 2.4976095004800003e-05, "max": 0.00047377600524479995, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00027473704505280003, "min": 0.00027473704505280003, "max": 0.0052115360576927994, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10499520000000001, "min": 0.10499520000000001, "max": 0.19475520000000002, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 1.1549472, "min": 1.1549472, "max": 2.1423072000000003, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00025926048000000007, "min": 0.00025926048000000007, "max": 0.00473828448, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.002851865280000001, "min": 0.002851865280000001, "max": 0.052121129280000005, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.421487603305785, "min": 5.471074380165289, "max": 25.643939393939394, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 3076.0, "min": 662.0, "max": 3385.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.16727263080187, "min": 5.416363651102239, "max": 25.38749987067598, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 3045.2399883270264, "min": 655.380001783371, "max": 3351.1499829292297, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710884704", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710885343" }, "total": 639.1794791719999, "count": 1, "self": 0.4459614469999451, "children": { "run_training.setup": { "total": 0.05607846600003086, "count": 1, "self": 0.05607846600003086 }, "TrainerController.start_learning": { "total": 638.6774392589999, "count": 1, "self": 0.7939845669967553, "children": { "TrainerController._reset_env": { "total": 3.313388814999996, "count": 1, "self": 3.313388814999996 }, "TrainerController.advance": { "total": 634.4802395490033, "count": 22735, "self": 0.3877439349959104, "children": { "env_step": { "total": 634.0924956140074, "count": 22735, "self": 425.3670566719989, "children": { "SubprocessEnvManager._take_step": { "total": 208.3177905190031, "count": 22735, "self": 2.023654673014562, "children": { "TorchPolicy.evaluate": { "total": 206.29413584598854, "count": 22735, "self": 206.29413584598854 } } }, "workers": { "total": 0.4076484230053552, "count": 22735, "self": 0.0, "children": { "worker_root": { "total": 637.022801565001, "count": 22735, "is_parallel": true, "self": 333.6983706249978, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006502191999970819, "count": 1, "is_parallel": true, "self": 0.004210124999929121, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022920670000416976, "count": 10, "is_parallel": true, "self": 0.0022920670000416976 } } }, "UnityEnvironment.step": { "total": 0.07240027000000282, "count": 1, "is_parallel": true, "self": 0.0070623309999859885, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000475819000030242, "count": 1, "is_parallel": true, "self": 0.000475819000030242 }, "communicator.exchange": { "total": 0.05653060899999218, "count": 1, "is_parallel": true, "self": 0.05653060899999218 }, "steps_from_proto": { "total": 0.008331510999994407, "count": 1, "is_parallel": true, "self": 0.0005112079999207708, "children": { "_process_rank_one_or_two_observation": { "total": 0.007820303000073636, "count": 10, "is_parallel": true, "self": 0.007820303000073636 } } } } } } }, "UnityEnvironment.step": { "total": 303.32443094000325, "count": 22734, "is_parallel": true, "self": 13.763931164990936, "children": { "UnityEnvironment._generate_step_input": { "total": 7.41276882199827, "count": 22734, "is_parallel": true, "self": 7.41276882199827 }, "communicator.exchange": { "total": 235.006582799003, "count": 22734, "is_parallel": true, "self": 235.006582799003 }, "steps_from_proto": { "total": 47.141148154011034, "count": 22734, "is_parallel": true, "self": 9.351318792005088, "children": { "_process_rank_one_or_two_observation": { "total": 37.789829362005946, "count": 227340, "is_parallel": true, "self": 37.789829362005946 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001587879999078723, "count": 1, "self": 0.0001587879999078723, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 626.9234541600687, "count": 892473, "is_parallel": true, "self": 19.042508660070098, "children": { "process_trajectory": { "total": 327.48031119899855, "count": 892473, "is_parallel": true, "self": 326.4386795559987, "children": { "RLTrainer._checkpoint": { "total": 1.041631642999846, "count": 5, "is_parallel": true, "self": 1.041631642999846 } } }, "_update_policy": { "total": 280.400634301, "count": 113, "is_parallel": true, "self": 83.15077945299748, "children": { "TorchPPOOptimizer.update": { "total": 197.24985484800254, "count": 7680, "is_parallel": true, "self": 197.24985484800254 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08966753999993671, "count": 1, "self": 0.0010097429999404994, "children": { "RLTrainer._checkpoint": { "total": 0.08865779699999621, "count": 1, "self": 0.08865779699999621 } } } } } } }