{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0770213603973389, "min": 1.0770213603973389, "max": 2.8692286014556885, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10295.2470703125, "min": 10295.2470703125, "max": 29383.76953125, "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": 13.134312629699707, "min": 0.5255668759346008, "max": 13.134312629699707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2561.19091796875, "min": 101.95997619628906, "max": 2630.82861328125, "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": 0.06541890625593105, "min": 0.06400486453893987, "max": 0.0749495964125826, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2616756250237242, "min": 0.25775686527748465, "max": 0.374747982062913, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17850451774018652, "min": 0.15080990298769856, "max": 0.2841753798372605, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7140180709607461, "min": 0.6032396119507942, "max": 1.4208768991863026, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082009730600007e-05, "min": 8.082009730600007e-05, "max": 0.0029188200027059994, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00032328038922400026, "min": 0.00032328038922400026, "max": 0.013851600038280001, "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": 26.34090909090909, "min": 3.8863636363636362, "max": 26.34090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1159.0, "min": 171.0, "max": 1409.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.34090909090909, "min": 3.8863636363636362, "max": 26.34090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1159.0, "min": 171.0, "max": 1409.0, "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": "1701214987", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701215471" }, "total": 484.5779421430001, "count": 1, "self": 0.44561009500012005, "children": { "run_training.setup": { "total": 0.05690376600000491, "count": 1, "self": 0.05690376600000491 }, "TrainerController.start_learning": { "total": 484.07542828199996, "count": 1, "self": 0.5626269460044568, "children": { "TrainerController._reset_env": { "total": 3.2509918590000098, "count": 1, "self": 3.2509918590000098 }, "TrainerController.advance": { "total": 480.12733807199515, "count": 18206, "self": 0.28799715400032255, "children": { "env_step": { "total": 479.83934091799483, "count": 18206, "self": 323.97691425600806, "children": { "SubprocessEnvManager._take_step": { "total": 155.5801327569891, "count": 18206, "self": 1.5030103499896086, "children": { "TorchPolicy.evaluate": { "total": 154.07712240699948, "count": 18206, "self": 154.07712240699948 } } }, "workers": { "total": 0.2822939049976867, "count": 18206, "self": 0.0, "children": { "worker_root": { "total": 482.65746393099187, "count": 18206, "is_parallel": true, "self": 238.2712203829925, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004954643000019132, "count": 1, "is_parallel": true, "self": 0.0034854269999868848, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014692160000322474, "count": 10, "is_parallel": true, "self": 0.0014692160000322474 } } }, "UnityEnvironment.step": { "total": 0.09962913499998649, "count": 1, "is_parallel": true, "self": 0.0006310179999218235, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041171500004111294, "count": 1, "is_parallel": true, "self": 0.00041171500004111294 }, "communicator.exchange": { "total": 0.09666716200001702, "count": 1, "is_parallel": true, "self": 0.09666716200001702 }, "steps_from_proto": { "total": 0.001919240000006539, "count": 1, "is_parallel": true, "self": 0.00035731900004520867, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015619209999613304, "count": 10, "is_parallel": true, "self": 0.0015619209999613304 } } } } } } }, "UnityEnvironment.step": { "total": 244.38624354799936, "count": 18205, "is_parallel": true, "self": 10.69244175298104, "children": { "UnityEnvironment._generate_step_input": { "total": 5.544226864007669, "count": 18205, "is_parallel": true, "self": 5.544226864007669 }, "communicator.exchange": { "total": 193.19105221900088, "count": 18205, "is_parallel": true, "self": 193.19105221900088 }, "steps_from_proto": { "total": 34.95852271200977, "count": 18205, "is_parallel": true, "self": 6.586937979970003, "children": { "_process_rank_one_or_two_observation": { "total": 28.371584732039764, "count": 182050, "is_parallel": true, "self": 28.371584732039764 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.688500017546176e-05, "count": 1, "self": 9.688500017546176e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 475.8698353220309, "count": 500861, "is_parallel": true, "self": 10.970185149002418, "children": { "process_trajectory": { "total": 272.8304832880284, "count": 500861, "is_parallel": true, "self": 266.212019982028, "children": { "RLTrainer._checkpoint": { "total": 6.618463306000422, "count": 40, "is_parallel": true, "self": 6.618463306000422 } } }, "_update_policy": { "total": 192.06916688500007, "count": 90, "is_parallel": true, "self": 59.8449678329971, "children": { "TorchPPOOptimizer.update": { "total": 132.22419905200297, "count": 4587, "is_parallel": true, "self": 132.22419905200297 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13437452000016492, "count": 1, "self": 0.0011754230001770338, "children": { "RLTrainer._checkpoint": { "total": 0.1331990969999879, "count": 1, "self": 0.1331990969999879 } } } } } } }