{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9073241949081421, "min": 0.8936873078346252, "max": 2.846449136734009, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8623.208984375, "min": 8597.2265625, "max": 29056.552734375, "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": 13.130393981933594, "min": 0.355713427066803, "max": 13.130393981933594, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2560.4267578125, "min": 69.00840759277344, "max": 2668.118408203125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06544553676533671, "min": 0.0646158230212909, "max": 0.07537605619633242, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26178214706134684, "min": 0.2584632920851636, "max": 0.3623076959509704, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20932065790482596, "min": 0.14936705389945748, "max": 0.2657391740410936, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8372826316193038, "min": 0.5974682155978299, "max": 1.3286958702054679, "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.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.363636363636363, "min": 4.113636363636363, "max": 26.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 181.0, "max": 1445.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 4.113636363636363, "max": 26.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 181.0, "max": 1445.0, "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": "1785243593", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/ml-agents/ml-agents/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1785244071" }, "total": 478.29277490100003, "count": 1, "self": 0.5381386160001966, "children": { "run_training.setup": { "total": 0.027295051999772113, "count": 1, "self": 0.027295051999772113 }, "TrainerController.start_learning": { "total": 477.72734123300006, "count": 1, "self": 0.41648384301242913, "children": { "TrainerController._reset_env": { "total": 3.364139183000134, "count": 1, "self": 3.364139183000134 }, "TrainerController.advance": { "total": 473.8629135789879, "count": 18192, "self": 0.4530396409941204, "children": { "env_step": { "total": 348.8511821770071, "count": 18192, "self": 273.96437511400654, "children": { "SubprocessEnvManager._take_step": { "total": 74.6482078980057, "count": 18192, "self": 1.357116676993428, "children": { "TorchPolicy.evaluate": { "total": 73.29109122101227, "count": 18192, "self": 73.29109122101227 } } }, "workers": { "total": 0.23859916499486644, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 475.7847337580574, "count": 18192, "is_parallel": true, "self": 235.37881344015295, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006219757000053505, "count": 1, "is_parallel": true, "self": 0.004759547999128699, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014602090009248059, "count": 10, "is_parallel": true, "self": 0.0014602090009248059 } } }, "UnityEnvironment.step": { "total": 0.03759560699973008, "count": 1, "is_parallel": true, "self": 0.0006115179999142129, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004044010001962306, "count": 1, "is_parallel": true, "self": 0.0004044010001962306 }, "communicator.exchange": { "total": 0.03476195399980497, "count": 1, "is_parallel": true, "self": 0.03476195399980497 }, "steps_from_proto": { "total": 0.0018177339998146635, "count": 1, "is_parallel": true, "self": 0.0003628360004768183, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014548979993378452, "count": 10, "is_parallel": true, "self": 0.0014548979993378452 } } } } } } }, "UnityEnvironment.step": { "total": 240.40592031790447, "count": 18191, "is_parallel": true, "self": 10.988991108889877, "children": { "UnityEnvironment._generate_step_input": { "total": 5.837349308021658, "count": 18191, "is_parallel": true, "self": 5.837349308021658 }, "communicator.exchange": { "total": 183.59168836101617, "count": 18191, "is_parallel": true, "self": 183.59168836101617 }, "steps_from_proto": { "total": 39.98789153997677, "count": 18191, "is_parallel": true, "self": 7.113355822866197, "children": { "_process_rank_one_or_two_observation": { "total": 32.874535717110575, "count": 181910, "is_parallel": true, "self": 32.874535717110575 } } } } } } } } } } }, "trainer_advance": { "total": 124.55869176098668, "count": 18192, "self": 0.49665611301770696, "children": { "process_trajectory": { "total": 25.78007191596771, "count": 18192, "self": 25.329791808968366, "children": { "RLTrainer._checkpoint": { "total": 0.45028010699934384, "count": 4, "self": 0.45028010699934384 } } }, "_update_policy": { "total": 98.28196373200126, "count": 90, "self": 40.69956661500919, "children": { "TorchPPOOptimizer.update": { "total": 57.58239711699207, "count": 4587, "self": 57.58239711699207 } } } } } } }, "trainer_threads": { "total": 1.2209998203616124e-06, "count": 1, "self": 1.2209998203616124e-06 }, "TrainerController._save_models": { "total": 0.08380340699977751, "count": 1, "self": 0.0008023059995139192, "children": { "RLTrainer._checkpoint": { "total": 0.08300110100026359, "count": 1, "self": 0.08300110100026359 } } } } } } }