{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0165377855300903, "min": 1.0165377855300903, "max": 2.870363712310791, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9694.720703125, "min": 9694.720703125, "max": 29584.83984375, "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": 12.607762336730957, "min": 0.2763255834579468, "max": 12.607762336730957, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2458.513671875, "min": 53.60716247558594, "max": 2538.610107421875, "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": 0.0726075234813513, "min": 0.06293807824612505, "max": 0.07613630079910816, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2904300939254052, "min": 0.2569936812844175, "max": 0.3709127338391173, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21715145718817616, "min": 0.09760081702295473, "max": 0.26717352995685506, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8686058287527046, "min": 0.3904032680918189, "max": 1.3358676497842752, "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": 24.931818181818183, "min": 3.022727272727273, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1097.0, "min": 133.0, "max": 1368.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.931818181818183, "min": 3.022727272727273, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1097.0, "min": 133.0, "max": 1368.0, "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": "1701026891", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701027446" }, "total": 555.1377120309999, "count": 1, "self": 0.7478855039998962, "children": { "run_training.setup": { "total": 0.09032947099990452, "count": 1, "self": 0.09032947099990452 }, "TrainerController.start_learning": { "total": 554.2994970560001, "count": 1, "self": 0.6918652370011387, "children": { "TrainerController._reset_env": { "total": 4.361812042999873, "count": 1, "self": 4.361812042999873 }, "TrainerController.advance": { "total": 549.093988334999, "count": 18205, "self": 0.345037779001359, "children": { "env_step": { "total": 548.7489505559977, "count": 18205, "self": 376.13263509802437, "children": { "SubprocessEnvManager._take_step": { "total": 172.27199197798086, "count": 18205, "self": 1.709202016993686, "children": { "TorchPolicy.evaluate": { "total": 170.56278996098717, "count": 18205, "self": 170.56278996098717 } } }, "workers": { "total": 0.34432347999245394, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 552.5358000410044, "count": 18205, "is_parallel": true, "self": 266.8546966410131, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008992700999897352, "count": 1, "is_parallel": true, "self": 0.006367535999970642, "children": { "_process_rank_one_or_two_observation": { "total": 0.00262516499992671, "count": 10, "is_parallel": true, "self": 0.00262516499992671 } } }, "UnityEnvironment.step": { "total": 0.03951231599990024, "count": 1, "is_parallel": true, "self": 0.0006805269997585128, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035833900005854957, "count": 1, "is_parallel": true, "self": 0.00035833900005854957 }, "communicator.exchange": { "total": 0.03633111900012409, "count": 1, "is_parallel": true, "self": 0.03633111900012409 }, "steps_from_proto": { "total": 0.0021423309999590856, "count": 1, "is_parallel": true, "self": 0.0004205840004942729, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017217469994648127, "count": 10, "is_parallel": true, "self": 0.0017217469994648127 } } } } } } }, "UnityEnvironment.step": { "total": 285.68110339999134, "count": 18204, "is_parallel": true, "self": 12.130947220015514, "children": { "UnityEnvironment._generate_step_input": { "total": 6.301458551003634, "count": 18204, "is_parallel": true, "self": 6.301458551003634 }, "communicator.exchange": { "total": 226.48012773298728, "count": 18204, "is_parallel": true, "self": 226.48012773298728 }, "steps_from_proto": { "total": 40.76856989598491, "count": 18204, "is_parallel": true, "self": 7.912287776922767, "children": { "_process_rank_one_or_two_observation": { "total": 32.85628211906214, "count": 182040, "is_parallel": true, "self": 32.85628211906214 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011737199997696734, "count": 1, "self": 0.00011737199997696734, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 544.2729118900013, "count": 564069, "is_parallel": true, "self": 13.087672984949222, "children": { "process_trajectory": { "total": 306.54531476205034, "count": 564069, "is_parallel": true, "self": 305.5792367920503, "children": { "RLTrainer._checkpoint": { "total": 0.9660779700000148, "count": 4, "is_parallel": true, "self": 0.9660779700000148 } } }, "_update_policy": { "total": 224.63992414300174, "count": 90, "is_parallel": true, "self": 77.26510237300022, "children": { "TorchPPOOptimizer.update": { "total": 147.37482177000152, "count": 4587, "is_parallel": true, "self": 147.37482177000152 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15171406900003603, "count": 1, "self": 0.001299314000107188, "children": { "RLTrainer._checkpoint": { "total": 0.15041475499992885, "count": 1, "self": 0.15041475499992885 } } } } } } }