{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2414430379867554, "min": 1.2414430379867554, "max": 2.8473098278045654, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 61956.6953125, "min": 61956.6953125, "max": 143823.3125, "count": 10 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 49936.0, "max": 499976.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 49936.0, "max": 499976.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.0325345993042, "min": 0.5359605550765991, "max": 13.0325345993042, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 13071.6318359375, "min": 531.6728515625, "max": 13071.6318359375, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 50347.0, "min": 48158.0, "max": 51939.0, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.723320158102766, "min": 4.595041322314049, "max": 26.723320158102766, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 6761.0, "min": 1112.0, "max": 6761.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.723320158102766, "min": 4.595041322314049, "max": 26.723320158102766, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 6761.0, "min": 1112.0, "max": 6761.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07133291598333302, "min": 0.0677069277278188, "max": 0.07191986645776563, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.42799749589999814, "min": 0.33853463863909405, "max": 0.4315191987465938, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1726221695749296, "min": 0.15932191979501997, "max": 0.26725991099288626, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0357330174495776, "min": 0.7966095989750999, "max": 1.6035594659573176, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00027792009444160007, "min": 0.00027792009444160007, "max": 0.00474737600505248, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0016675205666496005, "min": 0.0016675205666496005, "max": 0.0256227200875456, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1055584, "min": 0.1055584, "max": 0.19494751999999999, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6333504, "min": 0.5757312, "max": 1.1124544, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00028736416, "min": 0.00028736416, "max": 0.0047478812480000005, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0017241849599999998, "min": 0.0017241849599999998, "max": 0.02563147456, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1722222377", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722223550" }, "total": 1172.8241759060002, "count": 1, "self": 0.4347973820001698, "children": { "run_training.setup": { "total": 0.062018931000011435, "count": 1, "self": 0.062018931000011435 }, "TrainerController.start_learning": { "total": 1172.327359593, "count": 1, "self": 1.45369134800535, "children": { "TrainerController._reset_env": { "total": 2.8592593130000523, "count": 1, "self": 2.8592593130000523 }, "TrainerController.advance": { "total": 1167.9143520309945, "count": 45473, "self": 0.7339244770000732, "children": { "env_step": { "total": 1167.1804275539944, "count": 45473, "self": 830.8589418810001, "children": { "SubprocessEnvManager._take_step": { "total": 335.6040028889935, "count": 45473, "self": 3.692482988993447, "children": { "TorchPolicy.evaluate": { "total": 331.91151990000003, "count": 45473, "self": 331.91151990000003 } } }, "workers": { "total": 0.717482784000822, "count": 45473, "self": 0.0, "children": { "worker_root": { "total": 1169.313837148981, "count": 45473, "is_parallel": true, "self": 609.7622481829553, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0055547730000853335, "count": 1, "is_parallel": true, "self": 0.003897673000096802, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016570999999885316, "count": 10, "is_parallel": true, "self": 0.0016570999999885316 } } }, "UnityEnvironment.step": { "total": 0.036646482000037395, "count": 1, "is_parallel": true, "self": 0.0006977770001412864, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004922289999740315, "count": 1, "is_parallel": true, "self": 0.0004922289999740315 }, "communicator.exchange": { "total": 0.0333448750000116, "count": 1, "is_parallel": true, "self": 0.0333448750000116 }, "steps_from_proto": { "total": 0.002111600999910479, "count": 1, "is_parallel": true, "self": 0.00044369599993387965, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016679049999765994, "count": 10, "is_parallel": true, "self": 0.0016679049999765994 } } } } } } }, "UnityEnvironment.step": { "total": 559.5515889660257, "count": 45472, "is_parallel": true, "self": 25.547297212119474, "children": { "UnityEnvironment._generate_step_input": { "total": 13.661311461974037, "count": 45472, "is_parallel": true, "self": 13.661311461974037 }, "communicator.exchange": { "total": 435.7263184049739, "count": 45472, "is_parallel": true, "self": 435.7263184049739 }, "steps_from_proto": { "total": 84.61666188695835, "count": 45472, "is_parallel": true, "self": 16.224453627084472, "children": { "_process_rank_one_or_two_observation": { "total": 68.39220825987388, "count": 454720, "is_parallel": true, "self": 68.39220825987388 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012513000001490582, "count": 1, "self": 0.00012513000001490582, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1147.9487378497447, "count": 2318740, "is_parallel": true, "self": 49.54633950089283, "children": { "process_trajectory": { "total": 796.0291217058524, "count": 2318740, "is_parallel": true, "self": 794.4383031038524, "children": { "RLTrainer._checkpoint": { "total": 1.590818602000013, "count": 10, "is_parallel": true, "self": 1.590818602000013 } } }, "_update_policy": { "total": 302.3732766429995, "count": 57, "is_parallel": true, "self": 130.33788797099987, "children": { "TorchPPOOptimizer.update": { "total": 172.0353886719996, "count": 11469, "is_parallel": true, "self": 172.0353886719996 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09993177100000139, "count": 1, "self": 0.0009694459999991523, "children": { "RLTrainer._checkpoint": { "total": 0.09896232500000224, "count": 1, "self": 0.09896232500000224 } } } } } } }