{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4005649089813232, "min": 1.400559902191162, "max": 1.423022747039795, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69318.15625, "min": 69171.7109375, "max": 77583.1953125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 74.2781954887218, "min": 72.82865583456426, "max": 381.32824427480915, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49395.0, "min": 48823.0, "max": 50146.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999912.0, "min": 49551.0, "max": 1999912.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999912.0, "min": 49551.0, "max": 1999912.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4598238468170166, "min": -0.017649132758378983, "max": 2.529406785964966, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1635.7828369140625, "min": -2.2943873405456543, "max": 1656.81787109375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.774103899916312, "min": 1.756595253600524, "max": 4.05992748520591, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2509.7790934443474, "min": 228.35738296806812, "max": 2555.9108018279076, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.774103899916312, "min": 1.756595253600524, "max": 4.05992748520591, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2509.7790934443474, "min": 228.35738296806812, "max": 2555.9108018279076, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017002467262742963, "min": 0.013796134889384526, "max": 0.019925846910700783, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05100740178822889, "min": 0.0285852543291791, "max": 0.05460692363752363, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06140681045750777, "min": 0.025096339701364438, "max": 0.06565129198133945, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1842204313725233, "min": 0.050192679402728875, "max": 0.1842204313725233, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7081487639833295e-06, "min": 3.7081487639833295e-06, "max": 0.00029532832655722503, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1124446291949989e-05, "min": 1.1124446291949989e-05, "max": 0.0008442069185977001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123601666666666, "min": 0.10123601666666666, "max": 0.19844277500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30370805, "min": 0.20760825000000005, "max": 0.5814022999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.16772316666666e-05, "min": 7.16772316666666e-05, "max": 0.004922294472500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002150316949999998, "min": 0.0002150316949999998, "max": 0.014071974770000002, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688293482", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --force --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": "1688295817" }, "total": 2334.849885342, "count": 1, "self": 0.4348626260002675, "children": { "run_training.setup": { "total": 0.04074172399998588, "count": 1, "self": 0.04074172399998588 }, "TrainerController.start_learning": { "total": 2334.374280992, "count": 1, "self": 4.209305215938912, "children": { "TrainerController._reset_env": { "total": 4.072186880000004, "count": 1, "self": 4.072186880000004 }, "TrainerController.advance": { "total": 2325.971640867061, "count": 233212, "self": 4.305137629134151, "children": { "env_step": { "total": 1807.037929400944, "count": 233212, "self": 1525.613351927905, "children": { "SubprocessEnvManager._take_step": { "total": 278.79291001606816, "count": 233212, "self": 15.962208126051848, "children": { "TorchPolicy.evaluate": { "total": 262.8307018900163, "count": 222852, "self": 262.8307018900163 } } }, "workers": { "total": 2.631667456970888, "count": 233212, "self": 0.0, "children": { "worker_root": { "total": 2326.9812053719697, "count": 233212, "is_parallel": true, "self": 1076.8117207759256, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008478379999985464, "count": 1, "is_parallel": true, "self": 0.00024196699999379234, "children": { "_process_rank_one_or_two_observation": { "total": 0.000605871000004754, "count": 2, "is_parallel": true, "self": 0.000605871000004754 } } }, "UnityEnvironment.step": { "total": 0.028193415999993476, "count": 1, "is_parallel": true, "self": 0.0003176240000186681, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022333999999091247, "count": 1, "is_parallel": true, "self": 0.00022333999999091247 }, "communicator.exchange": { "total": 0.02696835899999428, "count": 1, "is_parallel": true, "self": 0.02696835899999428 }, "steps_from_proto": { "total": 0.0006840929999896161, "count": 1, "is_parallel": true, "self": 0.00020325399998455396, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004808390000050622, "count": 2, "is_parallel": true, "self": 0.0004808390000050622 } } } } } } }, "UnityEnvironment.step": { "total": 1250.1694845960442, "count": 233211, "is_parallel": true, "self": 38.245784349035375, "children": { "UnityEnvironment._generate_step_input": { "total": 77.14609044593803, "count": 233211, "is_parallel": true, "self": 77.14609044593803 }, "communicator.exchange": { "total": 1042.7467340230587, "count": 233211, "is_parallel": true, "self": 1042.7467340230587 }, "steps_from_proto": { "total": 92.03087577801207, "count": 233211, "is_parallel": true, "self": 32.595346863961396, "children": { "_process_rank_one_or_two_observation": { "total": 59.43552891405068, "count": 466422, "is_parallel": true, "self": 59.43552891405068 } } } } } } } } } } }, "trainer_advance": { "total": 514.628573836983, "count": 233212, "self": 6.373027049090638, "children": { "process_trajectory": { "total": 135.06735771689333, "count": 233212, "self": 133.65190018389328, "children": { "RLTrainer._checkpoint": { "total": 1.4154575330000512, "count": 10, "self": 1.4154575330000512 } } }, "_update_policy": { "total": 373.1881890709991, "count": 97, "self": 314.42117385800054, "children": { "TorchPPOOptimizer.update": { "total": 58.76701521299856, "count": 2910, "self": 58.76701521299856 } } } } } } }, "trainer_threads": { "total": 1.0839999049494509e-06, "count": 1, "self": 1.0839999049494509e-06 }, "TrainerController._save_models": { "total": 0.12114694499996403, "count": 1, "self": 0.0020496059996730764, "children": { "RLTrainer._checkpoint": { "total": 0.11909733900029096, "count": 1, "self": 0.11909733900029096 } } } } } } }