{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9728973507881165, "min": 0.9728973507881165, "max": 2.8724944591522217, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9332.03125, "min": 9332.03125, "max": 29385.619140625, "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": 12.94704818725586, "min": 0.38231411576271057, "max": 12.94704818725586, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2524.67431640625, "min": 74.16893768310547, "max": 2638.8681640625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07646885813338646, "min": 0.06252157294012231, "max": 0.07646885813338646, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3058754325335458, "min": 0.25008629176048924, "max": 0.3711118324301388, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20686868118012652, "min": 0.10011100374029804, "max": 0.27820880068283455, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8274747247205061, "min": 0.40044401496119214, "max": 1.3408698080217136, "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": 24.431818181818183, "min": 2.909090909090909, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1075.0, "min": 128.0, "max": 1418.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.431818181818183, "min": 2.909090909090909, "max": 25.78181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1075.0, "min": 128.0, "max": 1418.0, "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": "1694691055", "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": "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": "1694691541" }, "total": 485.68638191499997, "count": 1, "self": 0.4838326019998931, "children": { "run_training.setup": { "total": 0.06412441300005867, "count": 1, "self": 0.06412441300005867 }, "TrainerController.start_learning": { "total": 485.1384249, "count": 1, "self": 0.596966754991854, "children": { "TrainerController._reset_env": { "total": 4.87203182799999, "count": 1, "self": 4.87203182799999 }, "TrainerController.advance": { "total": 479.4190459640082, "count": 18218, "self": 0.2873944120105989, "children": { "env_step": { "total": 479.1316515519976, "count": 18218, "self": 348.49963910299357, "children": { "SubprocessEnvManager._take_step": { "total": 130.33845702200279, "count": 18218, "self": 1.8876270500059036, "children": { "TorchPolicy.evaluate": { "total": 128.45082997199688, "count": 18218, "self": 128.45082997199688 } } }, "workers": { "total": 0.2935554270012517, "count": 18218, "self": 0.0, "children": { "worker_root": { "total": 483.38332349099164, "count": 18218, "is_parallel": true, "self": 226.79782934100683, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00796103300001505, "count": 1, "is_parallel": true, "self": 0.005477673999962462, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024833590000525874, "count": 10, "is_parallel": true, "self": 0.0024833590000525874 } } }, "UnityEnvironment.step": { "total": 0.05178079500001331, "count": 1, "is_parallel": true, "self": 0.0007102710001163359, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042041899996547727, "count": 1, "is_parallel": true, "self": 0.00042041899996547727 }, "communicator.exchange": { "total": 0.043939468999951714, "count": 1, "is_parallel": true, "self": 0.043939468999951714 }, "steps_from_proto": { "total": 0.006710635999979786, "count": 1, "is_parallel": true, "self": 0.000559425999654195, "children": { "_process_rank_one_or_two_observation": { "total": 0.006151210000325591, "count": 10, "is_parallel": true, "self": 0.006151210000325591 } } } } } } }, "UnityEnvironment.step": { "total": 256.5854941499848, "count": 18217, "is_parallel": true, "self": 10.904825158999756, "children": { "UnityEnvironment._generate_step_input": { "total": 5.610329074991, "count": 18217, "is_parallel": true, "self": 5.610329074991 }, "communicator.exchange": { "total": 201.55449435399782, "count": 18217, "is_parallel": true, "self": 201.55449435399782 }, "steps_from_proto": { "total": 38.51584556199623, "count": 18217, "is_parallel": true, "self": 7.03463392501169, "children": { "_process_rank_one_or_two_observation": { "total": 31.48121163698454, "count": 182170, "is_parallel": true, "self": 31.48121163698454 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010186300005443627, "count": 1, "self": 0.00010186300005443627, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 475.73869168401643, "count": 442236, "is_parallel": true, "self": 10.321319236016848, "children": { "process_trajectory": { "total": 262.53325987699964, "count": 442236, "is_parallel": true, "self": 260.89952703699953, "children": { "RLTrainer._checkpoint": { "total": 1.633732840000107, "count": 4, "is_parallel": true, "self": 1.633732840000107 } } }, "_update_policy": { "total": 202.88411257099995, "count": 90, "is_parallel": true, "self": 79.86724014099241, "children": { "TorchPPOOptimizer.update": { "total": 123.01687243000754, "count": 4584, "is_parallel": true, "self": 123.01687243000754 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2502784899999142, "count": 1, "self": 0.0011213819999511543, "children": { "RLTrainer._checkpoint": { "total": 0.24915710799996305, "count": 1, "self": 0.24915710799996305 } } } } } } }