{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8986996412277222, "min": 0.8986996412277222, "max": 2.5502874851226807, "count": 4 }, "SnowballTarget.Policy.Entropy.sum": { "value": 44742.66015625, "min": 44742.66015625, "max": 128848.171875, "count": 4 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 49936.0, "max": 199984.0, "count": 4 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 49936.0, "max": 199984.0, "count": 4 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.738842964172363, "min": 2.5263326168060303, "max": 12.738842964172363, "count": 4 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 12649.6708984375, "min": 2506.1220703125, "max": 12649.6708984375, "count": 4 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 4 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 48158.0, "min": 48158.0, "max": 50347.0, "count": 4 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.04632755251758212, "min": 0.04430820485148698, "max": 0.04865574299783738, "count": 4 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 1.0192061553868066, "min": 0.9747805067327135, "max": 1.1190820889502597, "count": 4 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21243467427451498, "min": 0.21243467427451498, "max": 0.2734953221203624, "count": 4 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 4.67356283403933, "min": 4.67356283403933, "max": 6.290392408768336, "count": 4 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.037608740599999e-05, "min": 5.037608740599999e-05, "max": 0.00034957601260600005, "count": 4 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0011082739229319998, "min": 0.0011082739229319998, "max": 0.007690672277332001, "count": 4 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.11259400000000003, "min": 0.11259400000000003, "max": 0.18739400000000003, "count": 4 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 2.4770680000000005, "min": 2.4770680000000005, "max": 4.122668000000001, "count": 4 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0006384406, "min": 0.0006384406, "max": 0.0043709606, "count": 4 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.014045693199999999, "min": 0.014045693199999999, "max": 0.0961611332, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.21900826446281, "min": 8.962809917355372, "max": 25.21900826446281, "count": 4 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 6103.0, "min": 2169.0, "max": 6130.0, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.21900826446281, "min": 8.962809917355372, "max": 25.21900826446281, "count": 4 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 6103.0, "min": 2169.0, "max": 6130.0, "count": 4 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685729131", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1685729587" }, "total": 456.2128257029999, "count": 1, "self": 0.4278515199998765, "children": { "run_training.setup": { "total": 0.04437486500000887, "count": 1, "self": 0.04437486500000887 }, "TrainerController.start_learning": { "total": 455.740599318, "count": 1, "self": 0.5891577260024405, "children": { "TrainerController._reset_env": { "total": 4.61565690700013, "count": 1, "self": 4.61565690700013 }, "TrainerController.advance": { "total": 450.3961513479976, "count": 18197, "self": 0.30243467299783333, "children": { "env_step": { "total": 450.09371667499977, "count": 18197, "self": 314.2947311350115, "children": { "SubprocessEnvManager._take_step": { "total": 135.49346667000123, "count": 18197, "self": 1.8037477550094536, "children": { "TorchPolicy.evaluate": { "total": 133.68971891499177, "count": 18197, "self": 133.68971891499177 } } }, "workers": { "total": 0.30551886998705413, "count": 18197, "self": 0.0, "children": { "worker_root": { "total": 454.09914541900457, "count": 18197, "is_parallel": true, "self": 200.9775325099895, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005102915999941615, "count": 1, "is_parallel": true, "self": 0.0035525810001217906, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015503349998198246, "count": 10, "is_parallel": true, "self": 0.0015503349998198246 } } }, "UnityEnvironment.step": { "total": 0.06232388700004776, "count": 1, "is_parallel": true, "self": 0.0006328690001282666, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004490090000217606, "count": 1, "is_parallel": true, "self": 0.0004490090000217606 }, "communicator.exchange": { "total": 0.05718236799998522, "count": 1, "is_parallel": true, "self": 0.05718236799998522 }, "steps_from_proto": { "total": 0.004059640999912517, "count": 1, "is_parallel": true, "self": 0.0012361069998405583, "children": { "_process_rank_one_or_two_observation": { "total": 0.002823534000071959, "count": 10, "is_parallel": true, "self": 0.002823534000071959 } } } } } } }, "UnityEnvironment.step": { "total": 253.12161290901508, "count": 18196, "is_parallel": true, "self": 10.251260011047634, "children": { "UnityEnvironment._generate_step_input": { "total": 5.468177977974165, "count": 18196, "is_parallel": true, "self": 5.468177977974165 }, "communicator.exchange": { "total": 203.28468006399225, "count": 18196, "is_parallel": true, "self": 203.28468006399225 }, "steps_from_proto": { "total": 34.11749485600103, "count": 18196, "is_parallel": true, "self": 6.5729254689367735, "children": { "_process_rank_one_or_two_observation": { "total": 27.544569387064257, "count": 181960, "is_parallel": true, "self": 27.544569387064257 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.898800001588825e-05, "count": 1, "self": 8.898800001588825e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 446.73269791298026, "count": 449755, "is_parallel": true, "self": 10.09641651000834, "children": { "process_trajectory": { "total": 261.71174789797215, "count": 449755, "is_parallel": true, "self": 260.39681715597203, "children": { "RLTrainer._checkpoint": { "total": 1.314930742000115, "count": 2, "is_parallel": true, "self": 1.314930742000115 } } }, "_update_policy": { "total": 174.92453350499977, "count": 90, "is_parallel": true, "self": 81.10975437799993, "children": { "TorchPPOOptimizer.update": { "total": 93.81477912699984, "count": 2160, "is_parallel": true, "self": 93.81477912699984 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13954434899983426, "count": 1, "self": 0.0009534879998227552, "children": { "RLTrainer._checkpoint": { "total": 0.1385908610000115, "count": 1, "self": 0.1385908610000115 } } } } } } }