{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.400717854499817, "min": 1.400717854499817, "max": 1.4263628721237183, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70005.078125, "min": 68384.109375, "max": 76629.34375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.59927797833934, "min": 85.5, "max": 399.824, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49084.0, "min": 48823.0, "max": 50045.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999914.0, "min": 49435.0, "max": 1999914.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999914.0, "min": 49435.0, "max": 1999914.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.418498992919922, "min": 0.1370699554681778, "max": 2.418498992919922, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1339.848388671875, "min": 16.996673583984375, "max": 1361.72802734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8072656942834064, "min": 1.7212419120534774, "max": 3.903258511355815, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2109.225194633007, "min": 213.4339970946312, "max": 2152.9096898436546, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8072656942834064, "min": 1.7212419120534774, "max": 3.903258511355815, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2109.225194633007, "min": 213.4339970946312, "max": 2152.9096898436546, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016914685158634608, "min": 0.011981123487203149, "max": 0.020578136084239102, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050744055475903826, "min": 0.023962246974406298, "max": 0.06173440825271731, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053842300176620485, "min": 0.021174524600307148, "max": 0.05823269989341497, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16152690052986146, "min": 0.042349049200614296, "max": 0.17448555988570053, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.527748824116659e-06, "min": 3.527748824116659e-06, "max": 0.00029537137654287495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0583246472349978e-05, "min": 1.0583246472349978e-05, "max": 0.0008443062185645999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10117588333333333, "min": 0.10117588333333333, "max": 0.198457125, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30352765, "min": 0.20749310000000004, "max": 0.5814354, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.867657833333321e-05, "min": 6.867657833333321e-05, "max": 0.004923010537499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020602973499999965, "min": 0.00020602973499999965, "max": 0.014073626459999999, "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": "1709534779", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709537210" }, "total": 2431.324324962, "count": 1, "self": 0.43775394100021003, "children": { "run_training.setup": { "total": 0.0757391079999934, "count": 1, "self": 0.0757391079999934 }, "TrainerController.start_learning": { "total": 2430.8108319129997, "count": 1, "self": 4.487711923005918, "children": { "TrainerController._reset_env": { "total": 3.1492621589999885, "count": 1, "self": 3.1492621589999885 }, "TrainerController.advance": { "total": 2423.0532138359936, "count": 232040, "self": 4.921396852123053, "children": { "env_step": { "total": 1945.2837470428663, "count": 232040, "self": 1610.6733229119143, "children": { "SubprocessEnvManager._take_step": { "total": 331.721592724034, "count": 232040, "self": 17.402971074056723, "children": { "TorchPolicy.evaluate": { "total": 314.3186216499773, "count": 222946, "self": 314.3186216499773 } } }, "workers": { "total": 2.888831406917916, "count": 232040, "self": 0.0, "children": { "worker_root": { "total": 2423.4166817679748, "count": 232040, "is_parallel": true, "self": 1113.6644701789146, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010022710000043844, "count": 1, "is_parallel": true, "self": 0.0003006420000133403, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007016289999910441, "count": 2, "is_parallel": true, "self": 0.0007016289999910441 } } }, "UnityEnvironment.step": { "total": 0.030991054999958578, "count": 1, "is_parallel": true, "self": 0.0003822809999292076, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024298700003555496, "count": 1, "is_parallel": true, "self": 0.00024298700003555496 }, "communicator.exchange": { "total": 0.029612283000005846, "count": 1, "is_parallel": true, "self": 0.029612283000005846 }, "steps_from_proto": { "total": 0.00075350399998797, "count": 1, "is_parallel": true, "self": 0.00022294499996178274, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005305590000261873, "count": 2, "is_parallel": true, "self": 0.0005305590000261873 } } } } } } }, "UnityEnvironment.step": { "total": 1309.7522115890602, "count": 232039, "is_parallel": true, "self": 42.0839217401799, "children": { "UnityEnvironment._generate_step_input": { "total": 87.77631993500694, "count": 232039, "is_parallel": true, "self": 87.77631993500694 }, "communicator.exchange": { "total": 1085.1802133369665, "count": 232039, "is_parallel": true, "self": 1085.1802133369665 }, "steps_from_proto": { "total": 94.7117565769068, "count": 232039, "is_parallel": true, "self": 35.52359624296798, "children": { "_process_rank_one_or_two_observation": { "total": 59.18816033393881, "count": 464078, "is_parallel": true, "self": 59.18816033393881 } } } } } } } } } } }, "trainer_advance": { "total": 472.84806994100404, "count": 232040, "self": 6.730631702002199, "children": { "process_trajectory": { "total": 155.30905324299965, "count": 232040, "self": 154.04664250999997, "children": { "RLTrainer._checkpoint": { "total": 1.2624107329996832, "count": 10, "self": 1.2624107329996832 } } }, "_update_policy": { "total": 310.8083849960022, "count": 97, "self": 249.69704442400246, "children": { "TorchPPOOptimizer.update": { "total": 61.11134057199973, "count": 2910, "self": 61.11134057199973 } } } } } } }, "trainer_threads": { "total": 8.179999895219225e-07, "count": 1, "self": 8.179999895219225e-07 }, "TrainerController._save_models": { "total": 0.12064317700014726, "count": 1, "self": 0.002006343000175548, "children": { "RLTrainer._checkpoint": { "total": 0.11863683399997171, "count": 1, "self": 0.11863683399997171 } } } } } } }