{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9658316969871521, "min": 0.9658316969871521, "max": 2.8539516925811768, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9296.1298828125, "min": 9296.1298828125, "max": 29258.712890625, "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": 12.421199798583984, "min": 0.3404746949672699, "max": 12.421199798583984, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2422.134033203125, "min": 66.05209350585938, "max": 2506.89404296875, "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": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07329059722627897, "min": 0.06266246291639868, "max": 0.07329059722627897, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29316238890511587, "min": 0.25697454751478327, "max": 0.356729673227414, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.200471520971726, "min": 0.13467276993769167, "max": 0.2991287639328078, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.801886083886904, "min": 0.5386910797507667, "max": 1.495643819664039, "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": 24.727272727272727, "min": 3.590909090909091, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1088.0, "min": 158.0, "max": 1336.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.727272727272727, "min": 3.590909090909091, "max": 24.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1088.0, "min": 158.0, "max": 1336.0, "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": "1720713793", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget2 --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": "1720714266" }, "total": 473.126200315, "count": 1, "self": 0.5362746749997314, "children": { "run_training.setup": { "total": 0.05487586400022337, "count": 1, "self": 0.05487586400022337 }, "TrainerController.start_learning": { "total": 472.53504977600005, "count": 1, "self": 0.6183732779700222, "children": { "TrainerController._reset_env": { "total": 3.7607984589999433, "count": 1, "self": 3.7607984589999433 }, "TrainerController.advance": { "total": 468.0610161950299, "count": 18217, "self": 0.30333687701477174, "children": { "env_step": { "total": 467.7576793180151, "count": 18217, "self": 304.066618583965, "children": { "SubprocessEnvManager._take_step": { "total": 163.39061391703626, "count": 18217, "self": 1.5479140870411356, "children": { "TorchPolicy.evaluate": { "total": 161.84269982999513, "count": 18217, "self": 161.84269982999513 } } }, "workers": { "total": 0.30044681701383524, "count": 18217, "self": 0.0, "children": { "worker_root": { "total": 471.19467068703716, "count": 18217, "is_parallel": true, "self": 237.68778127498763, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002915173000019422, "count": 1, "is_parallel": true, "self": 0.0007603409990224463, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021548320009969757, "count": 10, "is_parallel": true, "self": 0.0021548320009969757 } } }, "UnityEnvironment.step": { "total": 0.04065685699970345, "count": 1, "is_parallel": true, "self": 0.0006692310003018065, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004118379997635202, "count": 1, "is_parallel": true, "self": 0.0004118379997635202 }, "communicator.exchange": { "total": 0.037453271999766, "count": 1, "is_parallel": true, "self": 0.037453271999766 }, "steps_from_proto": { "total": 0.002122515999872121, "count": 1, "is_parallel": true, "self": 0.00044022300016877125, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016822929997033498, "count": 10, "is_parallel": true, "self": 0.0016822929997033498 } } } } } } }, "UnityEnvironment.step": { "total": 233.50688941204953, "count": 18216, "is_parallel": true, "self": 10.659416914021676, "children": { "UnityEnvironment._generate_step_input": { "total": 5.49496116697992, "count": 18216, "is_parallel": true, "self": 5.49496116697992 }, "communicator.exchange": { "total": 182.9496659360084, "count": 18216, "is_parallel": true, "self": 182.9496659360084 }, "steps_from_proto": { "total": 34.40284539503955, "count": 18216, "is_parallel": true, "self": 6.639892713048084, "children": { "_process_rank_one_or_two_observation": { "total": 27.762952681991464, "count": 182160, "is_parallel": true, "self": 27.762952681991464 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014010899985805736, "count": 1, "self": 0.00014010899985805736, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 462.3029804179305, "count": 707785, "is_parallel": true, "self": 15.00239391093055, "children": { "process_trajectory": { "total": 256.2023142079993, "count": 707785, "is_parallel": true, "self": 255.15629369399903, "children": { "RLTrainer._checkpoint": { "total": 1.0460205140002472, "count": 4, "is_parallel": true, "self": 1.0460205140002472 } } }, "_update_policy": { "total": 191.09827229900066, "count": 90, "is_parallel": true, "self": 60.02271355300127, "children": { "TorchPPOOptimizer.update": { "total": 131.0755587459994, "count": 4587, "is_parallel": true, "self": 131.0755587459994 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09472173500034842, "count": 1, "self": 0.0009277440003643278, "children": { "RLTrainer._checkpoint": { "total": 0.09379399099998409, "count": 1, "self": 0.09379399099998409 } } } } } } }