{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9934631586074829, "min": 0.9934631586074829, "max": 2.853252649307251, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9562.0830078125, "min": 9562.0830078125, "max": 29251.546875, "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": 12.980531692504883, "min": 0.21412312984466553, "max": 12.980531692504883, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2531.20361328125, "min": 41.539886474609375, "max": 2612.998779296875, "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": 0.07052731139293766, "min": 0.06383202078723116, "max": 0.07311499782280959, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28210924557175066, "min": 0.25532808314892463, "max": 0.36557498911404795, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19464367372440358, "min": 0.11449711156356167, "max": 0.28225423103454067, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7785746948976143, "min": 0.4579884462542467, "max": 1.3690967431255416, "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": 25.954545454545453, "min": 3.0681818181818183, "max": 25.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1142.0, "min": 135.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.954545454545453, "min": 3.0681818181818183, "max": 25.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1142.0, "min": 135.0, "max": 1402.0, "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": "1698732163", "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": "1698732636" }, "total": 473.78148077700007, "count": 1, "self": 0.42574249900008, "children": { "run_training.setup": { "total": 0.04581934400005139, "count": 1, "self": 0.04581934400005139 }, "TrainerController.start_learning": { "total": 473.30991893399994, "count": 1, "self": 0.5920846750095734, "children": { "TrainerController._reset_env": { "total": 8.372173578000002, "count": 1, "self": 8.372173578000002 }, "TrainerController.advance": { "total": 464.25567320699054, "count": 18216, "self": 0.2869876789894761, "children": { "env_step": { "total": 463.96868552800106, "count": 18216, "self": 318.51026998399107, "children": { "SubprocessEnvManager._take_step": { "total": 145.1694984629995, "count": 18216, "self": 1.452669380008274, "children": { "TorchPolicy.evaluate": { "total": 143.71682908299124, "count": 18216, "self": 143.71682908299124 } } }, "workers": { "total": 0.2889170810104815, "count": 18216, "self": 0.0, "children": { "worker_root": { "total": 472.1078881550079, "count": 18216, "is_parallel": true, "self": 230.49510165100696, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005056796999951985, "count": 1, "is_parallel": true, "self": 0.003752883000061047, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013039139998909377, "count": 10, "is_parallel": true, "self": 0.0013039139998909377 } } }, "UnityEnvironment.step": { "total": 0.08263266899996324, "count": 1, "is_parallel": true, "self": 0.011658081000064158, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036846900002274197, "count": 1, "is_parallel": true, "self": 0.00036846900002274197 }, "communicator.exchange": { "total": 0.0684347929999376, "count": 1, "is_parallel": true, "self": 0.0684347929999376 }, "steps_from_proto": { "total": 0.0021713259999387446, "count": 1, "is_parallel": true, "self": 0.0004052899997759596, "children": { "_process_rank_one_or_two_observation": { "total": 0.001766036000162785, "count": 10, "is_parallel": true, "self": 0.001766036000162785 } } } } } } }, "UnityEnvironment.step": { "total": 241.61278650400095, "count": 18215, "is_parallel": true, "self": 10.557004159010035, "children": { "UnityEnvironment._generate_step_input": { "total": 5.395447192007282, "count": 18215, "is_parallel": true, "self": 5.395447192007282 }, "communicator.exchange": { "total": 192.02908073998753, "count": 18215, "is_parallel": true, "self": 192.02908073998753 }, "steps_from_proto": { "total": 33.6312544129961, "count": 18215, "is_parallel": true, "self": 6.337778801030595, "children": { "_process_rank_one_or_two_observation": { "total": 27.293475611965505, "count": 182150, "is_parallel": true, "self": 27.293475611965505 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0011430939998717804, "count": 1, "self": 0.0011430939998717804, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 460.29413958590646, "count": 489249, "is_parallel": true, "self": 10.430892579821375, "children": { "process_trajectory": { "total": 259.91536432908447, "count": 489249, "is_parallel": true, "self": 259.17583633708455, "children": { "RLTrainer._checkpoint": { "total": 0.7395279919999211, "count": 4, "is_parallel": true, "self": 0.7395279919999211 } } }, "_update_policy": { "total": 189.94788267700062, "count": 90, "is_parallel": true, "self": 58.05303393199267, "children": { "TorchPPOOptimizer.update": { "total": 131.89484874500795, "count": 4587, "is_parallel": true, "self": 131.89484874500795 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08884437999995498, "count": 1, "self": 0.0008490860000165412, "children": { "RLTrainer._checkpoint": { "total": 0.08799529399993844, "count": 1, "self": 0.08799529399993844 } } } } } } }