{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8540120124816895, "min": 0.8540120124816895, "max": 2.8858306407928467, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8802.3017578125, "min": 8562.8828125, "max": 27583.31640625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199936.0, "min": 9944.0, "max": 199936.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199936.0, "min": 9944.0, "max": 199936.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.656551361083984, "min": 0.18059249222278595, "max": 12.656551361083984, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2581.9365234375, "min": 11.91910457611084, "max": 2581.9365234375, "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": 2189.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07136784260427723, "min": 0.060519698533336816, "max": 0.0776025354086111, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3568392130213861, "min": 0.0776025354086111, "max": 0.3615068913398621, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19341688781392338, "min": 0.1399279706034006, "max": 0.2803054235729517, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9670844390696169, "min": 0.1573007811481754, "max": 1.3856700293573678, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.828097724000001e-06, "min": 6.828097724000001e-06, "max": 0.00028732800422399995, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.4140488620000006e-05, "min": 3.4140488620000006e-05, "max": 0.0013871400376199998, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10227599999999999, "min": 0.10227599999999999, "max": 0.19577599999999998, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.51138, "min": 0.19577599999999998, "max": 0.96238, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00012357240000000002, "min": 0.00012357240000000002, "max": 0.0047892224, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0006178620000000001, "min": 0.0006178620000000001, "max": 0.023122762000000005, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.163636363636364, "min": 3.8181818181818183, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1384.0, "min": 42.0, "max": 1384.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.163636363636364, "min": 3.8181818181818183, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1384.0, "min": 42.0, "max": 1384.0, "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": "1768142057", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/ruedi/miniconda3/envs/deep-rl-unit5/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1768142459" }, "total": 401.4754173329984, "count": 1, "self": 0.3207430079983169, "children": { "run_training.setup": { "total": 0.026407552000819123, "count": 1, "self": 0.026407552000819123 }, "TrainerController.start_learning": { "total": 401.12826677299927, "count": 1, "self": 0.5006365171302605, "children": { "TrainerController._reset_env": { "total": 2.4367559460006305, "count": 1, "self": 2.4367559460006305 }, "TrainerController.advance": { "total": 398.10597254486856, "count": 17672, "self": 0.22331890193163417, "children": { "env_step": { "total": 397.88265364293693, "count": 17672, "self": 252.57161869101765, "children": { "SubprocessEnvManager._take_step": { "total": 145.09750342501138, "count": 17672, "self": 1.2005272492133372, "children": { "TorchPolicy.evaluate": { "total": 143.89697617579805, "count": 17672, "self": 143.89697617579805 } } }, "workers": { "total": 0.21353152690790012, "count": 17672, "self": 0.0, "children": { "worker_root": { "total": 400.40890377600954, "count": 17672, "is_parallel": true, "self": 213.52285997986473, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028197029987495625, "count": 1, "is_parallel": true, "self": 0.0005475709949678276, "children": { "_process_rank_one_or_two_observation": { "total": 0.002272132003781735, "count": 10, "is_parallel": true, "self": 0.002272132003781735 } } }, "UnityEnvironment.step": { "total": 0.026516744999753428, "count": 1, "is_parallel": true, "self": 0.0009888280019367812, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046113799908198416, "count": 1, "is_parallel": true, "self": 0.00046113799908198416 }, "communicator.exchange": { "total": 0.023347678999925847, "count": 1, "is_parallel": true, "self": 0.023347678999925847 }, "steps_from_proto": { "total": 0.0017190999988088151, "count": 1, "is_parallel": true, "self": 0.00037836600131413434, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013407339974946808, "count": 10, "is_parallel": true, "self": 0.0013407339974946808 } } } } } } }, "UnityEnvironment.step": { "total": 186.8860437961448, "count": 17671, "is_parallel": true, "self": 9.02714470023966, "children": { "UnityEnvironment._generate_step_input": { "total": 5.126338234051218, "count": 17671, "is_parallel": true, "self": 5.126338234051218 }, "communicator.exchange": { "total": 143.59413328394112, "count": 17671, "is_parallel": true, "self": 143.59413328394112 }, "steps_from_proto": { "total": 29.138427577912807, "count": 17671, "is_parallel": true, "self": 5.871253660063303, "children": { "_process_rank_one_or_two_observation": { "total": 23.267173917849505, "count": 176710, "is_parallel": true, "self": 23.267173917849505 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0005407490007200977, "count": 1, "self": 0.0005407490007200977, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 394.9872860514297, "count": 467334, "is_parallel": true, "self": 8.543531348177567, "children": { "process_trajectory": { "total": 216.9490221782562, "count": 467334, "is_parallel": true, "self": 216.4556301782577, "children": { "RLTrainer._checkpoint": { "total": 0.4933919999984937, "count": 4, "is_parallel": true, "self": 0.4933919999984937 } } }, "_update_policy": { "total": 169.49473252499592, "count": 88, "is_parallel": true, "self": 35.334572824034694, "children": { "TorchPPOOptimizer.update": { "total": 134.16015970096123, "count": 4485, "is_parallel": true, "self": 134.16015970096123 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08436101599909307, "count": 1, "self": 0.000911858000108623, "children": { "RLTrainer._checkpoint": { "total": 0.08344915799898445, "count": 1, "self": 0.08344915799898445 } } } } } } }