{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.004270315170288, "min": 1.004270315170288, "max": 2.866438388824463, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9588.7734375, "min": 9588.7734375, "max": 29386.7265625, "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": 12.659043312072754, "min": 0.28123608231544495, "max": 12.659043312072754, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2468.513427734375, "min": 54.55979919433594, "max": 2576.88525390625, "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": 0.07398477366437231, "min": 0.06599234530985283, "max": 0.07462285321625864, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29593909465748924, "min": 0.2639693812394113, "max": 0.37311426608129317, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22443795613214082, "min": 0.12191020569070149, "max": 0.2965794730858476, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8977518245285633, "min": 0.48764082276280596, "max": 1.4211432217967277, "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": 24.818181818181817, "min": 3.6363636363636362, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1092.0, "min": 160.0, "max": 1345.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.818181818181817, "min": 3.6363636363636362, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1092.0, "min": 160.0, "max": 1345.0, "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": "1706200839", "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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706201262" }, "total": 422.4218304619999, "count": 1, "self": 0.427178978000029, "children": { "run_training.setup": { "total": 0.050298382999926616, "count": 1, "self": 0.050298382999926616 }, "TrainerController.start_learning": { "total": 421.94435310099993, "count": 1, "self": 0.5484763619997466, "children": { "TrainerController._reset_env": { "total": 1.9464728250000007, "count": 1, "self": 1.9464728250000007 }, "TrainerController.advance": { "total": 419.36326294000037, "count": 18199, "self": 0.2639022370085513, "children": { "env_step": { "total": 419.0993607029918, "count": 18199, "self": 269.08062153099627, "children": { "SubprocessEnvManager._take_step": { "total": 149.7492874699965, "count": 18199, "self": 1.403930135001474, "children": { "TorchPolicy.evaluate": { "total": 148.34535733499501, "count": 18199, "self": 148.34535733499501 } } }, "workers": { "total": 0.2694517019990599, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 420.85188283199955, "count": 18199, "is_parallel": true, "self": 208.69065455600207, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00268849200006116, "count": 1, "is_parallel": true, "self": 0.0007033400004274881, "children": { "_process_rank_one_or_two_observation": { "total": 0.001985151999633672, "count": 10, "is_parallel": true, "self": 0.001985151999633672 } } }, "UnityEnvironment.step": { "total": 0.03534112100010134, "count": 1, "is_parallel": true, "self": 0.0005917900000440568, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039994899998418987, "count": 1, "is_parallel": true, "self": 0.00039994899998418987 }, "communicator.exchange": { "total": 0.03247227199994995, "count": 1, "is_parallel": true, "self": 0.03247227199994995 }, "steps_from_proto": { "total": 0.0018771100001231389, "count": 1, "is_parallel": true, "self": 0.0003973830002905743, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014797269998325646, "count": 10, "is_parallel": true, "self": 0.0014797269998325646 } } } } } } }, "UnityEnvironment.step": { "total": 212.16122827599747, "count": 18198, "is_parallel": true, "self": 10.360083902950237, "children": { "UnityEnvironment._generate_step_input": { "total": 5.19808329501393, "count": 18198, "is_parallel": true, "self": 5.19808329501393 }, "communicator.exchange": { "total": 164.3864991410062, "count": 18198, "is_parallel": true, "self": 164.3864991410062 }, "steps_from_proto": { "total": 32.21656193702711, "count": 18198, "is_parallel": true, "self": 5.86967788210336, "children": { "_process_rank_one_or_two_observation": { "total": 26.34688405492375, "count": 181980, "is_parallel": true, "self": 26.34688405492375 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012539899989860714, "count": 1, "self": 0.00012539899989860714, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 413.8957417317911, "count": 652938, "is_parallel": true, "self": 13.68043667571942, "children": { "process_trajectory": { "total": 230.0237830100716, "count": 652938, "is_parallel": true, "self": 229.53637960707147, "children": { "RLTrainer._checkpoint": { "total": 0.48740340300014395, "count": 4, "is_parallel": true, "self": 0.48740340300014395 } } }, "_update_policy": { "total": 170.19152204600005, "count": 90, "is_parallel": true, "self": 47.745286473003034, "children": { "TorchPPOOptimizer.update": { "total": 122.44623557299701, "count": 4587, "is_parallel": true, "self": 122.44623557299701 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08601557499991941, "count": 1, "self": 0.0014051289997496497, "children": { "RLTrainer._checkpoint": { "total": 0.08461044600016976, "count": 1, "self": 0.08461044600016976 } } } } } } }