{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0079764127731323, "min": 1.0079764127731323, "max": 2.8579025268554688, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9646.333984375, "min": 9646.333984375, "max": 29299.216796875, "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": 12.721266746520996, "min": 0.15817871689796448, "max": 12.721266746520996, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2480.64697265625, "min": 30.68667221069336, "max": 2557.29541015625, "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": 0.06664608550839629, "min": 0.06220580712171938, "max": 0.0758219606700746, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26658434203358516, "min": 0.2613537428674046, "max": 0.379109803350373, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1927697587320033, "min": 0.12590989021027424, "max": 0.287019684267979, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7710790349280132, "min": 0.503639560841097, "max": 1.4350984213398952, "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": 25.886363636363637, "min": 3.5, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 154.0, "max": 1375.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 3.5, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 154.0, "max": 1375.0, "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": "1700231316", "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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700231802" }, "total": 486.008175911, "count": 1, "self": 0.4241429010000388, "children": { "run_training.setup": { "total": 0.06683947200002649, "count": 1, "self": 0.06683947200002649 }, "TrainerController.start_learning": { "total": 485.51719353799996, "count": 1, "self": 0.5652356580088167, "children": { "TrainerController._reset_env": { "total": 8.247341818999985, "count": 1, "self": 8.247341818999985 }, "TrainerController.advance": { "total": 476.61865872899114, "count": 18201, "self": 0.27455514998388253, "children": { "env_step": { "total": 476.34410357900725, "count": 18201, "self": 326.0370628590084, "children": { "SubprocessEnvManager._take_step": { "total": 150.0226456849981, "count": 18201, "self": 1.4922675679956683, "children": { "TorchPolicy.evaluate": { "total": 148.53037811700244, "count": 18201, "self": 148.53037811700244 } } }, "workers": { "total": 0.2843950350007276, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 484.0789747890015, "count": 18201, "is_parallel": true, "self": 235.87509858399795, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00594763399999465, "count": 1, "is_parallel": true, "self": 0.003751859999908902, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021957740000857484, "count": 10, "is_parallel": true, "self": 0.0021957740000857484 } } }, "UnityEnvironment.step": { "total": 0.035147657999971216, "count": 1, "is_parallel": true, "self": 0.0007239029999936974, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003625370000008843, "count": 1, "is_parallel": true, "self": 0.0003625370000008843 }, "communicator.exchange": { "total": 0.03219207399996549, "count": 1, "is_parallel": true, "self": 0.03219207399996549 }, "steps_from_proto": { "total": 0.001869144000011147, "count": 1, "is_parallel": true, "self": 0.0003607549999173898, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015083890000937572, "count": 10, "is_parallel": true, "self": 0.0015083890000937572 } } } } } } }, "UnityEnvironment.step": { "total": 248.20387620500355, "count": 18200, "is_parallel": true, "self": 10.77225088400212, "children": { "UnityEnvironment._generate_step_input": { "total": 5.572157363993085, "count": 18200, "is_parallel": true, "self": 5.572157363993085 }, "communicator.exchange": { "total": 196.23691317600566, "count": 18200, "is_parallel": true, "self": 196.23691317600566 }, "steps_from_proto": { "total": 35.62255478100269, "count": 18200, "is_parallel": true, "self": 6.705569982030227, "children": { "_process_rank_one_or_two_observation": { "total": 28.916984798972464, "count": 182000, "is_parallel": true, "self": 28.916984798972464 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011104899999736517, "count": 1, "self": 0.00011104899999736517, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 472.44711625701433, "count": 506219, "is_parallel": true, "self": 10.947201342031292, "children": { "process_trajectory": { "total": 267.31806510698345, "count": 506219, "is_parallel": true, "self": 266.49055126898344, "children": { "RLTrainer._checkpoint": { "total": 0.8275138380000158, "count": 4, "is_parallel": true, "self": 0.8275138380000158 } } }, "_update_policy": { "total": 194.18184980799958, "count": 90, "is_parallel": true, "self": 60.52484161400389, "children": { "TorchPPOOptimizer.update": { "total": 133.6570081939957, "count": 4587, "is_parallel": true, "self": 133.6570081939957 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0858462830000235, "count": 1, "self": 0.0008407650000208378, "children": { "RLTrainer._checkpoint": { "total": 0.08500551800000267, "count": 1, "self": 0.08500551800000267 } } } } } } }