{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7879202365875244, "min": 0.786651074886322, "max": 2.8786001205444336, "count": 100 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7514.39501953125, "min": 7514.39501953125, "max": 29543.07421875, "count": 100 }, "SnowballTarget.Step.mean": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Step.sum": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.509793281555176, "min": 0.052285898476839066, "max": 14.530828475952148, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2829.40966796875, "min": 10.143464088439941, "max": 2970.48876953125, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.266666666666666, "min": 2.840909090909091, "max": 28.763636363636362, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1272.0, "min": 125.0, "max": 1582.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.266666666666666, "min": 2.840909090909091, "max": 28.763636363636362, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1272.0, "min": 125.0, "max": 1582.0, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0348583965630193, "min": 0.02223999684671677, "max": 0.04416433579172008, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.0697167931260386, "min": 0.04447999369343354, "max": 0.12209505223048231, "count": 100 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14338716150571904, "min": 0.12423156294971704, "max": 0.34505327604711056, "count": 100 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.28677432301143807, "min": 0.2484631258994341, "max": 0.9872858139375846, "count": 100 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.0464099651199974e-05, "min": 1.0464099651199974e-05, "max": 0.0029804640006512, "count": 100 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.092819930239995e-05, "min": 2.092819930239995e-05, "max": 0.008683992010533602, "count": 100 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10034880000000002, "min": 0.10034880000000002, "max": 0.1993488, "count": 100 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.20069760000000003, "min": 0.20069760000000003, "max": 0.5894664000000001, "count": 100 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.7405119999999957e-05, "min": 2.7405119999999957e-05, "max": 0.00496750512, "count": 100 }, "SnowballTarget.Policy.Beta.sum": { "value": 5.4810239999999914e-05, "min": 5.4810239999999914e-05, "max": 0.01447437336, "count": 100 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708246879", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1708249064" }, "total": 2185.0026652879997, "count": 1, "self": 0.5593132280000646, "children": { "run_training.setup": { "total": 0.05087015499998415, "count": 1, "self": 0.05087015499998415 }, "TrainerController.start_learning": { "total": 2184.392481905, "count": 1, "self": 2.8296258870118436, "children": { "TrainerController._reset_env": { "total": 3.4611041020000357, "count": 1, "self": 3.4611041020000357 }, "TrainerController.advance": { "total": 2177.998655088988, "count": 90936, "self": 1.3659820560360458, "children": { "env_step": { "total": 2176.632673032952, "count": 90936, "self": 1381.6864568318629, "children": { "SubprocessEnvManager._take_step": { "total": 793.4833290320591, "count": 90936, "self": 7.470601420104117, "children": { "TorchPolicy.evaluate": { "total": 786.012727611955, "count": 90936, "self": 786.012727611955 } } }, "workers": { "total": 1.4628871690299547, "count": 90936, "self": 0.0, "children": { "worker_root": { "total": 2178.8881813100047, "count": 90936, "is_parallel": true, "self": 1033.063766807066, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006693552000001546, "count": 1, "is_parallel": true, "self": 0.004132064000089031, "children": { "_process_rank_one_or_two_observation": { "total": 0.002561487999912515, "count": 10, "is_parallel": true, "self": 0.002561487999912515 } } }, "UnityEnvironment.step": { "total": 0.04525442600004226, "count": 1, "is_parallel": true, "self": 0.0007054420000827122, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005453719999763962, "count": 1, "is_parallel": true, "self": 0.0005453719999763962 }, "communicator.exchange": { "total": 0.0418211389999783, "count": 1, "is_parallel": true, "self": 0.0418211389999783 }, "steps_from_proto": { "total": 0.0021824730000048476, "count": 1, "is_parallel": true, "self": 0.0004194029999666782, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017630700000381694, "count": 10, "is_parallel": true, "self": 0.0017630700000381694 } } } } } } }, "UnityEnvironment.step": { "total": 1145.8244145029387, "count": 90935, "is_parallel": true, "self": 55.586330102000375, "children": { "UnityEnvironment._generate_step_input": { "total": 28.834432134987367, "count": 90935, "is_parallel": true, "self": 28.834432134987367 }, "communicator.exchange": { "total": 879.1323398199252, "count": 90935, "is_parallel": true, "self": 879.1323398199252 }, "steps_from_proto": { "total": 182.2713124460259, "count": 90935, "is_parallel": true, "self": 33.14124962812127, "children": { "_process_rank_one_or_two_observation": { "total": 149.13006281790462, "count": 909350, "is_parallel": true, "self": 149.13006281790462 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002719849999266444, "count": 1, "self": 0.0002719849999266444, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2137.3701267639317, "count": 4541164, "is_parallel": true, "self": 100.80098829724375, "children": { "process_trajectory": { "total": 1542.0362937366895, "count": 4541164, "is_parallel": true, "self": 1538.803203035689, "children": { "RLTrainer._checkpoint": { "total": 3.233090701000606, "count": 20, "is_parallel": true, "self": 3.233090701000606 } } }, "_update_policy": { "total": 494.5328447299984, "count": 227, "is_parallel": true, "self": 249.2875851749942, "children": { "TorchPPOOptimizer.update": { "total": 245.24525955500417, "count": 5448, "is_parallel": true, "self": 245.24525955500417 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10282484200024555, "count": 1, "self": 0.0010113700004694692, "children": { "RLTrainer._checkpoint": { "total": 0.10181347199977608, "count": 1, "self": 0.10181347199977608 } } } } } } }