{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.801654815673828, "min": 2.7997958660125732, "max": 2.890307903289795, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4222.09375, "min": 1879.363525390625, "max": 4296.60595703125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 960.0, "max": 19992.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 960.0, "max": 19992.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.4630661010742188, "min": 0.054035332053899765, "max": 1.4630661010742188, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 38.03971862792969, "min": 0.8137731552124023, "max": 38.03971862792969, "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 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 9 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 2189.0, "min": 2189.0, "max": 2189.0, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07258494993313398, "min": 0.05907012469833717, "max": 0.08416848606886525, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.07258494993313398, "min": 0.05907012469833717, "max": 0.08416848606886525, "count": 9 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21661260315016204, "min": 0.06433110148645937, "max": 0.21661260315016204, "count": 9 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.21661260315016204, "min": 0.06433110148645937, "max": 0.21661260315016204, "count": 9 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 4.320098559999991e-06, "min": 4.320098559999991e-06, "max": 0.00026832001056, "count": 9 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.320098559999991e-06, "min": 4.320098559999991e-06, "max": 0.00026832001056, "count": 9 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10144, "min": 0.10144, "max": 0.18944000000000003, "count": 9 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10144, "min": 0.10144, "max": 0.18944000000000003, "count": 9 }, "SnowballTarget.Policy.Beta.mean": { "value": 8.185599999999986e-05, "min": 8.185599999999986e-05, "max": 0.0044730559999999996, "count": 9 }, "SnowballTarget.Policy.Beta.sum": { "value": 8.185599999999986e-05, "min": 8.185599999999986e-05, "max": 0.0044730559999999996, "count": 9 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 6.363636363636363, "min": 1.9090909090909092, "max": 6.363636363636363, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 70.0, "min": 6.0, "max": 70.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 6.363636363636363, "min": 1.9090909090909092, "max": 6.363636363636363, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 70.0, "min": 6.0, "max": 70.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683279866", "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=SnowballTarget2 --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": "1683279920" }, "total": 53.57713409799999, "count": 1, "self": 0.6897066520000408, "children": { "run_training.setup": { "total": 0.03874288199995135, "count": 1, "self": 0.03874288199995135 }, "TrainerController.start_learning": { "total": 52.848684563999996, "count": 1, "self": 0.07185487300466775, "children": { "TrainerController._reset_env": { "total": 3.8306307689999812, "count": 1, "self": 3.8306307689999812 }, "TrainerController.advance": { "total": 48.78620302299532, "count": 1874, "self": 0.028755773993907496, "children": { "env_step": { "total": 48.757447249001416, "count": 1874, "self": 35.38897093799119, "children": { "SubprocessEnvManager._take_step": { "total": 13.341887148011892, "count": 1874, "self": 0.1632166190136104, "children": { "TorchPolicy.evaluate": { "total": 13.178670528998282, "count": 1874, "self": 13.178670528998282 } } }, "workers": { "total": 0.02658916299833436, "count": 1874, "self": 0.0, "children": { "worker_root": { "total": 52.55357760500169, "count": 1874, "is_parallel": true, "self": 26.85210147700036, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017832309999903373, "count": 1, "is_parallel": true, "self": 0.0004351480001787422, "children": { "_process_rank_one_or_two_observation": { "total": 0.001348082999811595, "count": 10, "is_parallel": true, "self": 0.001348082999811595 } } }, "UnityEnvironment.step": { "total": 0.03532547099985095, "count": 1, "is_parallel": true, "self": 0.0005585599999449187, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031621499988432333, "count": 1, "is_parallel": true, "self": 0.00031621499988432333 }, "communicator.exchange": { "total": 0.032542380999984744, "count": 1, "is_parallel": true, "self": 0.032542380999984744 }, "steps_from_proto": { "total": 0.0019083150000369642, "count": 1, "is_parallel": true, "self": 0.0003870910002206074, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015212239998163568, "count": 10, "is_parallel": true, "self": 0.0015212239998163568 } } } } } } }, "UnityEnvironment.step": { "total": 25.70147612800133, "count": 1873, "is_parallel": true, "self": 1.013799609001353, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5504755020058383, "count": 1873, "is_parallel": true, "self": 0.5504755020058383 }, "communicator.exchange": { "total": 20.62665870399428, "count": 1873, "is_parallel": true, "self": 20.62665870399428 }, "steps_from_proto": { "total": 3.51054231299986, "count": 1873, "is_parallel": true, "self": 0.6997057490038969, "children": { "_process_rank_one_or_two_observation": { "total": 2.810836563995963, "count": 18730, "is_parallel": true, "self": 2.810836563995963 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022436899985223135, "count": 1, "self": 0.00022436899985223135, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 48.43041554401316, "count": 43769, "is_parallel": true, "self": 1.0189565230202788, "children": { "process_trajectory": { "total": 27.539691928992625, "count": 43769, "is_parallel": true, "self": 26.128432137992377, "children": { "RLTrainer._checkpoint": { "total": 1.4112597910002478, "count": 4, "is_parallel": true, "self": 1.4112597910002478 } } }, "_update_policy": { "total": 19.871767092000255, "count": 9, "is_parallel": true, "self": 7.773654529000169, "children": { "TorchPPOOptimizer.update": { "total": 12.098112563000086, "count": 456, "is_parallel": true, "self": 12.098112563000086 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15977153000017097, "count": 1, "self": 0.0008451560001958569, "children": { "RLTrainer._checkpoint": { "total": 0.1589263739999751, "count": 1, "self": 0.1589263739999751 } } } } } } }