{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.4463404715061188, "min": 0.44198188185691833, "max": 2.858366012573242, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4570.97265625, "min": 4220.04296875, "max": 29272.52734375, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.381290435791016, "min": 0.44299769401550293, "max": 14.49296760559082, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2948.16455078125, "min": 85.9415512084961, "max": 2956.0869140625, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07022065669176905, "min": 0.05862573398546517, "max": 0.08018968927253987, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.35110328345884523, "min": 0.23450293594186067, "max": 0.37917887281057616, "count": 200 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1488773824829681, "min": 0.1167021672042799, "max": 0.2613132029187445, "count": 200 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7443869124148406, "min": 0.4668086688171196, "max": 1.3065660145937226, "count": 200 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032997656000039e-07, "min": 7.032997656000039e-07, "max": 0.00029918820027059994, "count": 200 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.5164988280000196e-06, "min": 3.5164988280000196e-06, "max": 0.0014885028038323998, "count": 200 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10023440000000002, "min": 0.10023440000000002, "max": 0.1997294, "count": 200 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5011720000000001, "min": 0.4029176, "max": 0.9961676000000002, "count": 200 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.1696560000000067e-05, "min": 2.1696560000000067e-05, "max": 0.004986497059999999, "count": 200 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00010848280000000034, "min": 0.00010848280000000034, "max": 0.024808763240000004, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.01818181818182, "min": 3.4318181818181817, "max": 28.672727272727272, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1541.0, "min": 151.0, "max": 1577.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.01818181818182, "min": 3.4318181818181817, "max": 28.672727272727272, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1541.0, "min": 151.0, "max": 1577.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677949807", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677954217" }, "total": 4409.844330826, "count": 1, "self": 0.435766646999582, "children": { "run_training.setup": { "total": 0.11452621699999099, "count": 1, "self": 0.11452621699999099 }, "TrainerController.start_learning": { "total": 4409.294037962, "count": 1, "self": 5.548343260864385, "children": { "TrainerController._reset_env": { "total": 9.628526896999972, "count": 1, "self": 9.628526896999972 }, "TrainerController.advance": { "total": 4394.003285268136, "count": 181874, "self": 2.884884656184113, "children": { "env_step": { "total": 4391.118400611952, "count": 181874, "self": 3026.0863347660297, "children": { "SubprocessEnvManager._take_step": { "total": 1362.2840533749845, "count": 181874, "self": 15.09832740709976, "children": { "TorchPolicy.evaluate": { "total": 1347.1857259678848, "count": 181874, "self": 303.8104466318348, "children": { "TorchPolicy.sample_actions": { "total": 1043.37527933605, "count": 181874, "self": 1043.37527933605 } } } } }, "workers": { "total": 2.748012470937681, "count": 181874, "self": 0.0, "children": { "worker_root": { "total": 4394.140451260004, "count": 181874, "is_parallel": true, "self": 2074.9673888279794, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005091159000016887, "count": 1, "is_parallel": true, "self": 0.0037842739999973674, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013068850000195198, "count": 10, "is_parallel": true, "self": 0.0013068850000195198 } } }, "UnityEnvironment.step": { "total": 0.03441534300003468, "count": 1, "is_parallel": true, "self": 0.0006376890000296953, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041394499999114487, "count": 1, "is_parallel": true, "self": 0.00041394499999114487 }, "communicator.exchange": { "total": 0.03155768800002079, "count": 1, "is_parallel": true, "self": 0.03155768800002079 }, "steps_from_proto": { "total": 0.001806020999993052, "count": 1, "is_parallel": true, "self": 0.0004159989999266145, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013900220000664376, "count": 10, "is_parallel": true, "self": 0.0013900220000664376 } } } } } } }, "UnityEnvironment.step": { "total": 2319.1730624320244, "count": 181873, "is_parallel": true, "self": 94.96030460516249, "children": { "UnityEnvironment._generate_step_input": { "total": 50.881631307026396, "count": 181873, "is_parallel": true, "self": 50.881631307026396 }, "communicator.exchange": { "total": 1871.5105096879433, "count": 181873, "is_parallel": true, "self": 1871.5105096879433 }, "steps_from_proto": { "total": 301.82061683189187, "count": 181873, "is_parallel": true, "self": 67.24958293268895, "children": { "_process_rank_one_or_two_observation": { "total": 234.57103389920292, "count": 1818730, "is_parallel": true, "self": 234.57103389920292 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00025184300011460437, "count": 1, "self": 0.00025184300011460437, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 4363.76793783879, "count": 3938950, "is_parallel": true, "self": 92.59512234825434, "children": { "process_trajectory": { "total": 2495.746151783542, "count": 3938950, "is_parallel": true, "self": 2485.759414826542, "children": { "RLTrainer._checkpoint": { "total": 9.986736956999607, "count": 40, "is_parallel": true, "self": 9.986736956999607 } } }, "_update_policy": { "total": 1775.4266637069945, "count": 909, "is_parallel": true, "self": 613.5322511210611, "children": { "TorchPPOOptimizer.update": { "total": 1161.8944125859334, "count": 46344, "is_parallel": true, "self": 1161.8944125859334 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11363069300023199, "count": 1, "self": 0.0008440889996563783, "children": { "RLTrainer._checkpoint": { "total": 0.11278660400057561, "count": 1, "self": 0.11278660400057561 } } } } } } }