{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.790194034576416, "min": 2.790194034576416, "max": 2.86930251121521, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 28727.837890625, "min": 28727.837890625, "max": 29416.08984375, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.1893409490585327, "min": 0.4076758623123169, "max": 1.1893409490585327, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 243.8148956298828, "min": 79.08911895751953, "max": 243.8148956298828, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07217225737934796, "min": 0.07127089017797283, "max": 0.07217225737934796, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3608612868967398, "min": 0.28508356071189134, "max": 0.3608612868967398, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1923298097708646, "min": 0.11501921352236441, "max": 0.1923298097708646, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.961649048854323, "min": 0.46007685408945764, "max": 0.961649048854323, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032007656e-05, "min": 7.032007656e-05, "max": 0.00021882002706000002, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003516003828, "min": 0.0003516003828, "max": 0.0008752801082400001, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12344000000000002, "min": 0.12344000000000002, "max": 0.17294, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6172000000000001, "min": 0.6172000000000001, "max": 0.69176, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011796560000000003, "min": 0.0011796560000000003, "max": 0.003649706, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005898280000000001, "min": 0.005898280000000001, "max": 0.014598824, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 5.254545454545455, "min": 3.1363636363636362, "max": 5.254545454545455, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 289.0, "min": 138.0, "max": 289.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 5.254545454545455, "min": 3.1363636363636362, "max": 5.254545454545455, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 289.0, "min": 138.0, "max": 289.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1752289812", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/config/ppo/SnowballTarget.yaml --env=training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget_1 --no-graphics --force --torch-device=cpu", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752289870" }, "total": 57.713132589, "count": 1, "self": 0.5348000570000977, "children": { "run_training.setup": { "total": 0.02518352499998855, "count": 1, "self": 0.02518352499998855 }, "TrainerController.start_learning": { "total": 57.15314900699991, "count": 1, "self": 0.1125119459978805, "children": { "TrainerController._reset_env": { "total": 2.0932173139999577, "count": 1, "self": 2.0932173139999577 }, "TrainerController.advance": { "total": 54.86769369300225, "count": 1874, "self": 0.0403073840017214, "children": { "env_step": { "total": 54.82738630900053, "count": 1874, "self": 42.71046044700847, "children": { "SubprocessEnvManager._take_step": { "total": 12.078420897996011, "count": 1874, "self": 0.1969339619964785, "children": { "TorchPolicy.evaluate": { "total": 11.881486935999533, "count": 1874, "self": 11.881486935999533 } } }, "workers": { "total": 0.03850496399604708, "count": 1874, "self": 0.0, "children": { "worker_root": { "total": 56.894470702999456, "count": 1874, "is_parallel": true, "self": 26.552223479996997, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028823290000445922, "count": 1, "is_parallel": true, "self": 0.0009565029998839236, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019258260001606686, "count": 10, "is_parallel": true, "self": 0.0019258260001606686 } } }, "UnityEnvironment.step": { "total": 0.040668374000006224, "count": 1, "is_parallel": true, "self": 0.0006900830001086433, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044481899999482266, "count": 1, "is_parallel": true, "self": 0.00044481899999482266 }, "communicator.exchange": { "total": 0.03732375199990656, "count": 1, "is_parallel": true, "self": 0.03732375199990656 }, "steps_from_proto": { "total": 0.002209719999996196, "count": 1, "is_parallel": true, "self": 0.0004343550000385221, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017753649999576737, "count": 10, "is_parallel": true, "self": 0.0017753649999576737 } } } } } } }, "UnityEnvironment.step": { "total": 30.34224722300246, "count": 1873, "is_parallel": true, "self": 1.3598270850025074, "children": { "UnityEnvironment._generate_step_input": { "total": 0.6986923150000166, "count": 1873, "is_parallel": true, "self": 0.6986923150000166 }, "communicator.exchange": { "total": 23.950976189000585, "count": 1873, "is_parallel": true, "self": 23.950976189000585 }, "steps_from_proto": { "total": 4.332751633999351, "count": 1873, "is_parallel": true, "self": 0.883745305999696, "children": { "_process_rank_one_or_two_observation": { "total": 3.449006327999655, "count": 18730, "is_parallel": true, "self": 3.449006327999655 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00048037899989594735, "count": 1, "self": 0.00048037899989594735, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 54.2553477410022, "count": 79441, "is_parallel": true, "self": 1.6314657050151027, "children": { "process_trajectory": { "total": 30.552161239986845, "count": 79441, "is_parallel": true, "self": 30.226724156986847, "children": { "RLTrainer._checkpoint": { "total": 0.3254370829999971, "count": 2, "is_parallel": true, "self": 0.3254370829999971 } } }, "_update_policy": { "total": 22.07172079600025, "count": 9, "is_parallel": true, "self": 6.376189884000837, "children": { "TorchPPOOptimizer.update": { "total": 15.695530911999413, "count": 456, "is_parallel": true, "self": 15.695530911999413 } } } } } } } } }, "TrainerController._save_models": { "total": 0.07924567499992463, "count": 1, "self": 0.0010519239999666752, "children": { "RLTrainer._checkpoint": { "total": 0.07819375099995796, "count": 1, "self": 0.07819375099995796 } } } } } } }