{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.423821210861206, "min": 1.4190664291381836, "max": 1.423821210861206, "count": 4 }, "Huggy.Policy.Entropy.sum": { "value": 70047.734375, "min": 68564.7890625, "max": 77754.90625, "count": 4 }, "Huggy.Environment.EpisodeLength.mean": { "value": 230.05990783410138, "min": 230.05990783410138, "max": 406.8861788617886, "count": 4 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49923.0, "min": 49478.0, "max": 50080.0, "count": 4 }, "Huggy.Step.mean": { "value": 199992.0, "min": 49947.0, "max": 199992.0, "count": 4 }, "Huggy.Step.sum": { "value": 199992.0, "min": 49947.0, "max": 199992.0, "count": 4 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8986622095108032, "min": 0.07460981607437134, "max": 0.8986622095108032, "count": 4 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 195.00970458984375, "min": 9.102397918701172, "max": 195.00970458984375, "count": 4 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.2933797877505078, "min": 1.833546322510868, "max": 3.2933797877505078, "count": 4 }, "Huggy.Environment.CumulativeReward.sum": { "value": 714.6634139418602, "min": 223.69265134632587, "max": 714.6634139418602, "count": 4 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.2933797877505078, "min": 1.833546322510868, "max": 3.2933797877505078, "count": 4 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 714.6634139418602, "min": 223.69265134632587, "max": 714.6634139418602, "count": 4 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014468230124233135, "min": 0.014468230124233135, "max": 0.01799517210521218, "count": 4 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.02893646024846627, "min": 0.02893646024846627, "max": 0.05398551631563654, "count": 4 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.026294824046393238, "min": 0.021919104425857462, "max": 0.028443139636268218, "count": 4 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.052589648092786476, "min": 0.043838208851714924, "max": 0.07307288901259501, "count": 4 }, "Huggy.Policy.LearningRate.mean": { "value": 0.000273529283823575, "min": 0.000273529283823575, "max": 0.0002952804015732, "count": 4 }, "Huggy.Policy.LearningRate.sum": { "value": 0.00054705856764715, "min": 0.00054705856764715, "max": 0.0008437236187587998, "count": 4 }, "Huggy.Policy.Epsilon.mean": { "value": 0.19117642500000004, "min": 0.19117642500000004, "max": 0.19842680000000001, "count": 4 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3823528500000001, "min": 0.3823528500000001, "max": 0.5812412, "count": 4 }, "Huggy.Policy.Beta.mean": { "value": 0.0045597036075, "min": 0.0045597036075, "max": 0.00492149732, "count": 4 }, "Huggy.Policy.Beta.sum": { "value": 0.009119407215, "min": 0.009119407215, "max": 0.014063935880000003, "count": 4 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1763310354", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.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": "1763310613" }, "total": 259.3432807009999, "count": 1, "self": 0.4830919629998789, "children": { "run_training.setup": { "total": 0.02540454200016029, "count": 1, "self": 0.02540454200016029 }, "TrainerController.start_learning": { "total": 258.8347841959999, "count": 1, "self": 0.43272949203264943, "children": { "TrainerController._reset_env": { "total": 3.5080423469999005, "count": 1, "self": 3.5080423469999005 }, "TrainerController.advance": { "total": 254.8932644569668, "count": 23689, "self": 0.45385130094291526, "children": { "env_step": { "total": 215.56824009102093, "count": 23689, "self": 171.9124859079966, "children": { "SubprocessEnvManager._take_step": { "total": 43.37427502898527, "count": 23689, "self": 1.5959830879937726, "children": { "TorchPolicy.evaluate": { "total": 41.778291940991494, "count": 23339, "self": 41.778291940991494 } } }, "workers": { "total": 0.28147915403906154, "count": 23689, "self": 0.0, "children": { "worker_root": { "total": 257.4733873230016, "count": 23689, "is_parallel": true, "self": 118.62030745898437, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000843426000301406, "count": 1, "is_parallel": true, "self": 0.0002643500006342947, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005790759996671113, "count": 2, "is_parallel": true, "self": 0.0005790759996671113 } } }, "UnityEnvironment.step": { "total": 0.029022094000083598, "count": 1, "is_parallel": true, "self": 0.00033737000012479257, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020290999964345247, "count": 1, "is_parallel": true, "self": 0.00020290999964345247 }, "communicator.exchange": { "total": 0.02769276600020021, "count": 1, "is_parallel": true, "self": 0.02769276600020021 }, "steps_from_proto": { "total": 0.0007890480001151445, "count": 1, "is_parallel": true, "self": 0.00022475600007965113, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005642920000354934, "count": 2, "is_parallel": true, "self": 0.0005642920000354934 } } } } } } }, "UnityEnvironment.step": { "total": 138.85307986401722, "count": 23688, "is_parallel": true, "self": 3.8605985319613865, "children": { "UnityEnvironment._generate_step_input": { "total": 8.51409830502007, "count": 23688, "is_parallel": true, "self": 8.51409830502007 }, "communicator.exchange": { "total": 117.28334450301236, "count": 23688, "is_parallel": true, "self": 117.28334450301236 }, "steps_from_proto": { "total": 9.195038524023403, "count": 23688, "is_parallel": true, "self": 3.241506134007068, "children": { "_process_rank_one_or_two_observation": { "total": 5.953532390016335, "count": 47376, "is_parallel": true, "self": 5.953532390016335 } } } } } } } } } } }, "trainer_advance": { "total": 38.87117306500295, "count": 23689, "self": 0.7076474229975247, "children": { "process_trajectory": { "total": 11.622941843005265, "count": 23689, "self": 11.46507861600503, "children": { "RLTrainer._checkpoint": { "total": 0.15786322700023447, "count": 1, "self": 0.15786322700023447 } } }, "_update_policy": { "total": 26.54058379900016, "count": 10, "self": 20.773874048999915, "children": { "TorchPPOOptimizer.update": { "total": 5.7667097500002455, "count": 270, "self": 5.7667097500002455 } } } } } } }, "trainer_threads": { "total": 1.229000190505758e-06, "count": 1, "self": 1.229000190505758e-06 }, "TrainerController._save_models": { "total": 0.0007466710003427579, "count": 1, "self": 2.422400029900018e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0007224470000437577, "count": 1, "self": 0.0007224470000437577 } } } } } } }