{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9518494606018066, "min": 0.9518494606018066, "max": 2.8678529262542725, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9077.7880859375, "min": 9077.7880859375, "max": 29401.228515625, "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": 12.49244499206543, "min": 0.2776184678077698, "max": 12.49244499206543, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2436.02685546875, "min": 53.85798263549805, "max": 2535.77001953125, "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": 0.07026681232627216, "min": 0.06310081788034558, "max": 0.07551836997440124, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28106724930508864, "min": 0.25281136583695724, "max": 0.36417595998557534, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21673861423543855, "min": 0.09779241129952282, "max": 0.30504645266953634, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8669544569417542, "min": 0.3911696451980913, "max": 1.5252322633476818, "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": 24.818181818181817, "min": 3.25, "max": 24.818181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1092.0, "min": 143.0, "max": 1349.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.818181818181817, "min": 3.25, "max": 24.818181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1092.0, "min": 143.0, "max": 1349.0, "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": "1685260315", "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": "1685260894" }, "total": 579.135158579, "count": 1, "self": 0.43881860099997994, "children": { "run_training.setup": { "total": 0.04577784299999621, "count": 1, "self": 0.04577784299999621 }, "TrainerController.start_learning": { "total": 578.650562135, "count": 1, "self": 0.7611031769962437, "children": { "TrainerController._reset_env": { "total": 4.185800846999996, "count": 1, "self": 4.185800846999996 }, "TrainerController.advance": { "total": 573.5417530000037, "count": 18200, "self": 0.3706912849984292, "children": { "env_step": { "total": 573.1710617150053, "count": 18200, "self": 417.58510212399875, "children": { "SubprocessEnvManager._take_step": { "total": 155.20593660700928, "count": 18200, "self": 2.1788941250043763, "children": { "TorchPolicy.evaluate": { "total": 153.0270424820049, "count": 18200, "self": 153.0270424820049 } } }, "workers": { "total": 0.3800229839972644, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 576.6256451759971, "count": 18200, "is_parallel": true, "self": 266.6492646559956, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005725726999969538, "count": 1, "is_parallel": true, "self": 0.003994504999923265, "children": { "_process_rank_one_or_two_observation": { "total": 0.001731222000046273, "count": 10, "is_parallel": true, "self": 0.001731222000046273 } } }, "UnityEnvironment.step": { "total": 0.041888576000019384, "count": 1, "is_parallel": true, "self": 0.0006713470000363486, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005197570000063934, "count": 1, "is_parallel": true, "self": 0.0005197570000063934 }, "communicator.exchange": { "total": 0.037969465999992735, "count": 1, "is_parallel": true, "self": 0.037969465999992735 }, "steps_from_proto": { "total": 0.002728005999983907, "count": 1, "is_parallel": true, "self": 0.0007148729999926218, "children": { "_process_rank_one_or_two_observation": { "total": 0.002013132999991285, "count": 10, "is_parallel": true, "self": 0.002013132999991285 } } } } } } }, "UnityEnvironment.step": { "total": 309.9763805200015, "count": 18199, "is_parallel": true, "self": 12.400935440007913, "children": { "UnityEnvironment._generate_step_input": { "total": 6.793284724000955, "count": 18199, "is_parallel": true, "self": 6.793284724000955 }, "communicator.exchange": { "total": 247.5847066079969, "count": 18199, "is_parallel": true, "self": 247.5847066079969 }, "steps_from_proto": { "total": 43.19745374799572, "count": 18199, "is_parallel": true, "self": 8.669485755000835, "children": { "_process_rank_one_or_two_observation": { "total": 34.52796799299489, "count": 181990, "is_parallel": true, "self": 34.52796799299489 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017785900001854316, "count": 1, "self": 0.00017785900001854316, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 568.7143431229433, "count": 550590, "is_parallel": true, "self": 13.836509634930508, "children": { "process_trajectory": { "total": 316.2100532760135, "count": 550590, "is_parallel": true, "self": 315.2458851940135, "children": { "RLTrainer._checkpoint": { "total": 0.9641680820000147, "count": 4, "is_parallel": true, "self": 0.9641680820000147 } } }, "_update_policy": { "total": 238.6677802119993, "count": 90, "is_parallel": true, "self": 90.52631944299895, "children": { "TorchPPOOptimizer.update": { "total": 148.14146076900033, "count": 4587, "is_parallel": true, "self": 148.14146076900033 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1617272519999915, "count": 1, "self": 0.0009557350000477527, "children": { "RLTrainer._checkpoint": { "total": 0.16077151699994374, "count": 1, "self": 0.16077151699994374 } } } } } } }