{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4095345735549927, "min": 1.4095345735549927, "max": 1.429002285003662, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70314.6328125, "min": 69301.96875, "max": 77440.0546875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 94.11931818181819, "min": 77.53301886792453, "max": 424.58474576271186, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49695.0, "min": 49032.0, "max": 50101.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999504.0, "min": 49469.0, "max": 1999504.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999504.0, "min": 49469.0, "max": 1999504.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4194324016571045, "min": 0.03494935855269432, "max": 2.5170862674713135, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1277.4603271484375, "min": 4.089075088500977, "max": 1577.832763671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.766838090324944, "min": 1.8981877231699789, "max": 3.9976772955450857, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1988.8905116915703, "min": 222.08796361088753, "max": 2484.8413819670677, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.766838090324944, "min": 1.8981877231699789, "max": 3.9976772955450857, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1988.8905116915703, "min": 222.08796361088753, "max": 2484.8413819670677, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017044959262744266, "min": 0.011708193809075357, "max": 0.020314624354311184, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051134877788232794, "min": 0.023416387618150715, "max": 0.06094387306293356, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0473566627336873, "min": 0.02359049885223309, "max": 0.062210370165606335, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1420699882010619, "min": 0.04718099770446618, "max": 0.18535495835045973, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6069487977166615e-06, "min": 3.6069487977166615e-06, "max": 0.0002953209015597, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0820846393149984e-05, "min": 1.0820846393149984e-05, "max": 0.0008440818186393999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120228333333332, "min": 0.10120228333333332, "max": 0.19844029999999993, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30360685, "min": 0.20760060000000002, "max": 0.5813606, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.999393833333324e-05, "min": 6.999393833333324e-05, "max": 0.004922170969999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020998181499999973, "min": 0.00020998181499999973, "max": 0.014069893940000001, "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": "1721119189", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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": "1721121653" }, "total": 2463.372778719, "count": 1, "self": 0.4459227230004217, "children": { "run_training.setup": { "total": 0.08624345700002323, "count": 1, "self": 0.08624345700002323 }, "TrainerController.start_learning": { "total": 2462.8406125389997, "count": 1, "self": 4.4586329670046325, "children": { "TrainerController._reset_env": { "total": 3.291905004, "count": 1, "self": 3.291905004 }, "TrainerController.advance": { "total": 2454.9815325949953, "count": 232574, "self": 4.776521860046159, "children": { "env_step": { "total": 1949.9042828878896, "count": 232574, "self": 1610.6559369157128, "children": { "SubprocessEnvManager._take_step": { "total": 336.36428421699657, "count": 232574, "self": 17.607907797064286, "children": { "TorchPolicy.evaluate": { "total": 318.7563764199323, "count": 223020, "self": 318.7563764199323 } } }, "workers": { "total": 2.884061755180255, "count": 232574, "self": 0.0, "children": { "worker_root": { "total": 2455.5402808140807, "count": 232574, "is_parallel": true, "self": 1159.707617359989, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001016372999970372, "count": 1, "is_parallel": true, "self": 0.0002835450000020501, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007328279999683218, "count": 2, "is_parallel": true, "self": 0.0007328279999683218 } } }, "UnityEnvironment.step": { "total": 0.031238836999932573, "count": 1, "is_parallel": true, "self": 0.000385584999889943, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002456409999922471, "count": 1, "is_parallel": true, "self": 0.0002456409999922471 }, "communicator.exchange": { "total": 0.029833290000055968, "count": 1, "is_parallel": true, "self": 0.029833290000055968 }, "steps_from_proto": { "total": 0.0007743209999944156, "count": 1, "is_parallel": true, "self": 0.00021128200012299203, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005630389998714236, "count": 2, "is_parallel": true, "self": 0.0005630389998714236 } } } } } } }, "UnityEnvironment.step": { "total": 1295.8326634540917, "count": 232573, "is_parallel": true, "self": 39.92361381795513, "children": { "UnityEnvironment._generate_step_input": { "total": 83.64764788611387, "count": 232573, "is_parallel": true, "self": 83.64764788611387 }, "communicator.exchange": { "total": 1079.2265262389474, "count": 232573, "is_parallel": true, "self": 1079.2265262389474 }, "steps_from_proto": { "total": 93.03487551107537, "count": 232573, "is_parallel": true, "self": 35.24089099516641, "children": { "_process_rank_one_or_two_observation": { "total": 57.79398451590896, "count": 465146, "is_parallel": true, "self": 57.79398451590896 } } } } } } } } } } }, "trainer_advance": { "total": 500.30072784705965, "count": 232574, "self": 6.829434780956831, "children": { "process_trajectory": { "total": 159.34400702110338, "count": 232574, "self": 157.838646497102, "children": { "RLTrainer._checkpoint": { "total": 1.5053605240013894, "count": 10, "self": 1.5053605240013894 } } }, "_update_policy": { "total": 334.12728604499944, "count": 97, "self": 269.9630194449992, "children": { "TorchPPOOptimizer.update": { "total": 64.16426660000025, "count": 2910, "self": 64.16426660000025 } } } } } } }, "trainer_threads": { "total": 1.047999830916524e-06, "count": 1, "self": 1.047999830916524e-06 }, "TrainerController._save_models": { "total": 0.10854092499994294, "count": 1, "self": 0.001988426000025356, "children": { "RLTrainer._checkpoint": { "total": 0.10655249899991759, "count": 1, "self": 0.10655249899991759 } } } } } } }