{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.0538735389709473, "min": 2.0538735389709473, "max": 2.8903074264526367, "count": 15 }, "SnowballTarget.Policy.Entropy.sum": { "value": 21056.3125, "min": 20229.134765625, "max": 29631.431640625, "count": 15 }, "SnowballTarget.Step.mean": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Step.sum": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 4.231385707855225, "min": 0.14891785383224487, "max": 4.231385707855225, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 867.43408203125, "min": 28.890064239501953, "max": 867.43408203125, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 16.70909090909091, "min": 2.772727272727273, "max": 16.70909090909091, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 919.0, "min": 122.0, "max": 919.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 16.70909090909091, "min": 2.772727272727273, "max": 16.70909090909091, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 919.0, "min": 122.0, "max": 919.0, "count": 15 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0417517071046556, "min": 0.028716993547034993, "max": 0.0417517071046556, "count": 14 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.0417517071046556, "min": 0.028716993547034993, "max": 0.0417517071046556, "count": 14 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1918023142963648, "min": 0.05151942378235242, "max": 0.1918023142963648, "count": 14 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.1918023142963648, "min": 0.05151942378235242, "max": 0.1918023142963648, "count": 14 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.784097738666682e-06, "min": 6.784097738666682e-06, "max": 0.0002781760072746666, "count": 14 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 6.784097738666682e-06, "min": 6.784097738666682e-06, "max": 0.0002781760072746666, "count": 14 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10226133333333333, "min": 0.10226133333333333, "max": 0.19272533333333328, "count": 14 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10226133333333333, "min": 0.10226133333333333, "max": 0.19272533333333328, "count": 14 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00012284053333333356, "min": 0.00012284053333333356, "max": 0.004636994133333332, "count": 14 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00012284053333333356, "min": 0.00012284053333333356, "max": 0.004636994133333332, "count": 14 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694415126", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1694415518" }, "total": 392.46705395899994, "count": 1, "self": 0.43804733899969506, "children": { "run_training.setup": { "total": 0.045349221000151374, "count": 1, "self": 0.045349221000151374 }, "TrainerController.start_learning": { "total": 391.9836573990001, "count": 1, "self": 0.40211090198567945, "children": { "TrainerController._reset_env": { "total": 4.966020559000071, "count": 1, "self": 4.966020559000071 }, "TrainerController.advance": { "total": 386.4663362260146, "count": 13673, "self": 0.18922777101215615, "children": { "env_step": { "total": 386.27710845500246, "count": 13673, "self": 294.864554015011, "children": { "SubprocessEnvManager._take_step": { "total": 91.2114447800052, "count": 13673, "self": 1.5385142060122234, "children": { "TorchPolicy.evaluate": { "total": 89.67293057399297, "count": 13673, "self": 89.67293057399297 } } }, "workers": { "total": 0.20110965998628672, "count": 13673, "self": 0.0, "children": { "worker_root": { "total": 390.8088132300145, "count": 13673, "is_parallel": true, "self": 206.00392812802852, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005855769999925542, "count": 1, "is_parallel": true, "self": 0.004332075999855078, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015236940000704635, "count": 10, "is_parallel": true, "self": 0.0015236940000704635 } } }, "UnityEnvironment.step": { "total": 0.07767605899994123, "count": 1, "is_parallel": true, "self": 0.0006785279997529869, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002907699999923352, "count": 1, "is_parallel": true, "self": 0.0002907699999923352 }, "communicator.exchange": { "total": 0.06470752500013077, "count": 1, "is_parallel": true, "self": 0.06470752500013077 }, "steps_from_proto": { "total": 0.011999236000065139, "count": 1, "is_parallel": true, "self": 0.0004810750003798603, "children": { "_process_rank_one_or_two_observation": { "total": 0.011518160999685279, "count": 10, "is_parallel": true, "self": 0.011518160999685279 } } } } } } }, "UnityEnvironment.step": { "total": 184.80488510198597, "count": 13672, "is_parallel": true, "self": 8.064186371970209, "children": { "UnityEnvironment._generate_step_input": { "total": 4.114863584999284, "count": 13672, "is_parallel": true, "self": 4.114863584999284 }, "communicator.exchange": { "total": 145.3036681260187, "count": 13672, "is_parallel": true, "self": 145.3036681260187 }, "steps_from_proto": { "total": 27.32216701899779, "count": 13672, "is_parallel": true, "self": 4.87594188099888, "children": { "_process_rank_one_or_two_observation": { "total": 22.44622513799891, "count": 136720, "is_parallel": true, "self": 22.44622513799891 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019342899986440898, "count": 1, "self": 0.00019342899986440898, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 382.64629510903796, "count": 441885, "is_parallel": true, "self": 9.926138596034662, "children": { "process_trajectory": { "total": 250.18197013000372, "count": 441885, "is_parallel": true, "self": 248.3950705140037, "children": { "RLTrainer._checkpoint": { "total": 1.786899616000028, "count": 5, "is_parallel": true, "self": 1.786899616000028 } } }, "_update_policy": { "total": 122.53818638299958, "count": 14, "is_parallel": true, "self": 87.85068394299901, "children": { "TorchPPOOptimizer.update": { "total": 34.68750244000057, "count": 1704, "is_parallel": true, "self": 34.68750244000057 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14899628299986034, "count": 1, "self": 0.0008628309999494377, "children": { "RLTrainer._checkpoint": { "total": 0.1481334519999109, "count": 1, "self": 0.1481334519999109 } } } } } } }