{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7869897484779358, "min": 0.7869897484779358, "max": 2.8448987007141113, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7505.521484375, "min": 7505.521484375, "max": 29322.37109375, "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": 12.71745777130127, "min": 0.4550056755542755, "max": 12.71745777130127, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2479.904296875, "min": 88.27110290527344, "max": 2552.6279296875, "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": 0.07713902592727476, "min": 0.06210611525742684, "max": 0.07713902592727476, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.308556103709099, "min": 0.26258609417994855, "max": 0.3613618711516371, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17199772048522444, "min": 0.16756195206350336, "max": 0.297679300401725, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6879908819408977, "min": 0.6702478082540134, "max": 1.450596257167704, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.0776097306000005e-05, "min": 1.0776097306000005e-05, "max": 0.000389176002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.310438922400002e-05, "min": 4.310438922400002e-05, "max": 0.0018468800382800002, "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": 0.00011749060000000011, "min": 0.00011749060000000011, "max": 0.0038920306, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00046996240000000045, "min": 0.00046996240000000045, "max": 0.018472628, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.704545454545453, "min": 4.681818181818182, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1131.0, "min": 206.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.704545454545453, "min": 4.681818181818182, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1131.0, "min": 206.0, "max": 1387.0, "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": "1690751169", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690751648" }, "total": 479.7468599859999, "count": 1, "self": 0.8346768819999397, "children": { "run_training.setup": { "total": 0.05773264700007985, "count": 1, "self": 0.05773264700007985 }, "TrainerController.start_learning": { "total": 478.85445045699987, "count": 1, "self": 0.5752379669980883, "children": { "TrainerController._reset_env": { "total": 5.710226145000092, "count": 1, "self": 5.710226145000092 }, "TrainerController.advance": { "total": 472.32918590500174, "count": 18211, "self": 0.2719988109947735, "children": { "env_step": { "total": 472.05718709400696, "count": 18211, "self": 343.02013193199593, "children": { "SubprocessEnvManager._take_step": { "total": 128.74731361300837, "count": 18211, "self": 1.8049659520085015, "children": { "TorchPolicy.evaluate": { "total": 126.94234766099987, "count": 18211, "self": 126.94234766099987 } } }, "workers": { "total": 0.28974154900265603, "count": 18211, "self": 0.0, "children": { "worker_root": { "total": 477.0000466210041, "count": 18211, "is_parallel": true, "self": 222.23394213699407, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006611163000002307, "count": 1, "is_parallel": true, "self": 0.0044102199996132185, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022009430003890884, "count": 10, "is_parallel": true, "self": 0.0022009430003890884 } } }, "UnityEnvironment.step": { "total": 0.037755860999936885, "count": 1, "is_parallel": true, "self": 0.0006086119998371942, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033177800003159064, "count": 1, "is_parallel": true, "self": 0.00033177800003159064 }, "communicator.exchange": { "total": 0.034762788000080036, "count": 1, "is_parallel": true, "self": 0.034762788000080036 }, "steps_from_proto": { "total": 0.0020526829999880647, "count": 1, "is_parallel": true, "self": 0.0005000889998427738, "children": { "_process_rank_one_or_two_observation": { "total": 0.001552594000145291, "count": 10, "is_parallel": true, "self": 0.001552594000145291 } } } } } } }, "UnityEnvironment.step": { "total": 254.76610448401004, "count": 18210, "is_parallel": true, "self": 10.695643158006419, "children": { "UnityEnvironment._generate_step_input": { "total": 5.341359437999017, "count": 18210, "is_parallel": true, "self": 5.341359437999017 }, "communicator.exchange": { "total": 203.05249510500425, "count": 18210, "is_parallel": true, "self": 203.05249510500425 }, "steps_from_proto": { "total": 35.67660678300035, "count": 18210, "is_parallel": true, "self": 6.6271154439983775, "children": { "_process_rank_one_or_two_observation": { "total": 29.049491339001975, "count": 182100, "is_parallel": true, "self": 29.049491339001975 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015682299999753013, "count": 1, "self": 0.00015682299999753013, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 468.65139006295146, "count": 447220, "is_parallel": true, "self": 10.180057552867993, "children": { "process_trajectory": { "total": 257.292774075084, "count": 447220, "is_parallel": true, "self": 255.75812329808412, "children": { "RLTrainer._checkpoint": { "total": 1.5346507769999107, "count": 4, "is_parallel": true, "self": 1.5346507769999107 } } }, "_update_policy": { "total": 201.17855843499945, "count": 90, "is_parallel": true, "self": 79.28438403999974, "children": { "TorchPPOOptimizer.update": { "total": 121.89417439499971, "count": 4584, "is_parallel": true, "self": 121.89417439499971 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23964361699995607, "count": 1, "self": 0.0012411689999680675, "children": { "RLTrainer._checkpoint": { "total": 0.238402447999988, "count": 1, "self": 0.238402447999988 } } } } } } }