{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9552035331726074, "min": 0.9552035331726074, "max": 2.859280586242676, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9120.283203125, "min": 9120.283203125, "max": 29281.892578125, "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": 12.490450859069824, "min": 0.3208141624927521, "max": 12.490450859069824, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2435.637939453125, "min": 62.23794937133789, "max": 2521.7255859375, "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": 0.06592358961215189, "min": 0.06187757328399468, "max": 0.07327456886294599, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26369435844860756, "min": 0.24751029313597872, "max": 0.36637284431472994, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2248989751233774, "min": 0.12299293752042942, "max": 0.27458658814430237, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8995959004935096, "min": 0.4919717500817177, "max": 1.3729329407215118, "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": 25.5, "min": 3.909090909090909, "max": 25.5, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1122.0, "min": 172.0, "max": 1331.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.5, "min": 3.909090909090909, "max": 25.5, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1122.0, "min": 172.0, "max": 1331.0, "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": "1717408662", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717409162" }, "total": 499.08979235900006, "count": 1, "self": 0.43057547900002646, "children": { "run_training.setup": { "total": 0.0678474339999866, "count": 1, "self": 0.0678474339999866 }, "TrainerController.start_learning": { "total": 498.59136944600004, "count": 1, "self": 0.6816201650069615, "children": { "TrainerController._reset_env": { "total": 2.9359712619999527, "count": 1, "self": 2.9359712619999527 }, "TrainerController.advance": { "total": 494.8699719519931, "count": 18200, "self": 0.34331169098891223, "children": { "env_step": { "total": 494.52666026100417, "count": 18200, "self": 323.96356753201144, "children": { "SubprocessEnvManager._take_step": { "total": 170.21702881799365, "count": 18200, "self": 1.6542631750088503, "children": { "TorchPolicy.evaluate": { "total": 168.5627656429848, "count": 18200, "self": 168.5627656429848 } } }, "workers": { "total": 0.34606391099907796, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 497.19662469200057, "count": 18200, "is_parallel": true, "self": 250.96530961299447, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007274400000028436, "count": 1, "is_parallel": true, "self": 0.00566514999991341, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016092500001150256, "count": 10, "is_parallel": true, "self": 0.0016092500001150256 } } }, "UnityEnvironment.step": { "total": 0.08845052999993186, "count": 1, "is_parallel": true, "self": 0.008766793999939182, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004283800000166593, "count": 1, "is_parallel": true, "self": 0.0004283800000166593 }, "communicator.exchange": { "total": 0.07704882699999871, "count": 1, "is_parallel": true, "self": 0.07704882699999871 }, "steps_from_proto": { "total": 0.0022065289999773086, "count": 1, "is_parallel": true, "self": 0.0004019649999236208, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018045640000536878, "count": 10, "is_parallel": true, "self": 0.0018045640000536878 } } } } } } }, "UnityEnvironment.step": { "total": 246.2313150790061, "count": 18199, "is_parallel": true, "self": 11.0322445600018, "children": { "UnityEnvironment._generate_step_input": { "total": 5.8559890370041785, "count": 18199, "is_parallel": true, "self": 5.8559890370041785 }, "communicator.exchange": { "total": 193.13393515499524, "count": 18199, "is_parallel": true, "self": 193.13393515499524 }, "steps_from_proto": { "total": 36.20914632700487, "count": 18199, "is_parallel": true, "self": 6.916659714036541, "children": { "_process_rank_one_or_two_observation": { "total": 29.292486612968332, "count": 181990, "is_parallel": true, "self": 29.292486612968332 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019009800007552258, "count": 1, "self": 0.00019009800007552258, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 488.77967704303035, "count": 733216, "is_parallel": true, "self": 15.733688764016165, "children": { "process_trajectory": { "total": 272.3729013410144, "count": 733216, "is_parallel": true, "self": 271.47016660001475, "children": { "RLTrainer._checkpoint": { "total": 0.9027347409996764, "count": 4, "is_parallel": true, "self": 0.9027347409996764 } } }, "_update_policy": { "total": 200.67308693799976, "count": 90, "is_parallel": true, "self": 62.576724421993504, "children": { "TorchPPOOptimizer.update": { "total": 138.09636251600625, "count": 4587, "is_parallel": true, "self": 138.09636251600625 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10361596899997494, "count": 1, "self": 0.0009253639998405561, "children": { "RLTrainer._checkpoint": { "total": 0.10269060500013438, "count": 1, "self": 0.10269060500013438 } } } } } } }