{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.407245397567749, "min": 1.407245397567749, "max": 1.428560733795166, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69759.96875, "min": 68332.7109375, "max": 77736.9921875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.02707275803722, "min": 72.5544267053701, "max": 386.03846153846155, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49660.0, "min": 48744.0, "max": 50185.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999558.0, "min": 49880.0, "max": 1999558.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999558.0, "min": 49880.0, "max": 1999558.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.467963218688965, "min": 0.06762397289276123, "max": 2.4848506450653076, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1458.5662841796875, "min": 8.723492622375488, "max": 1641.693359375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9463722481945442, "min": 1.8318506668704424, "max": 3.979809810196767, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2332.3059986829758, "min": 236.30873602628708, "max": 2551.0008414387703, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9463722481945442, "min": 1.8318506668704424, "max": 3.979809810196767, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2332.3059986829758, "min": 236.30873602628708, "max": 2551.0008414387703, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016195674133349613, "min": 0.013947892123057196, "max": 0.019743804332695923, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.048587022400048835, "min": 0.027895784246114393, "max": 0.058660959932603875, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05524318536950482, "min": 0.023073339462280275, "max": 0.0629142432163159, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16572955610851448, "min": 0.04614667892456055, "max": 0.17443630658090115, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.619998793366665e-06, "min": 3.619998793366665e-06, "max": 0.00029530912656362503, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0859996380099996e-05, "min": 1.0859996380099996e-05, "max": 0.0008440713186428999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120663333333335, "min": 0.10120663333333335, "max": 0.19843637500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30361990000000005, "min": 0.20754490000000006, "max": 0.5813571000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.021100333333329e-05, "min": 7.021100333333329e-05, "max": 0.0049219751125, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021063300999999988, "min": 0.00021063300999999988, "max": 0.014069719290000005, "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": "1685183589", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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 --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": "1685185997" }, "total": 2408.058255895, "count": 1, "self": 0.528934339999978, "children": { "run_training.setup": { "total": 0.06445976200006953, "count": 1, "self": 0.06445976200006953 }, "TrainerController.start_learning": { "total": 2407.464861793, "count": 1, "self": 4.324351483960527, "children": { "TrainerController._reset_env": { "total": 4.355758695999953, "count": 1, "self": 4.355758695999953 }, "TrainerController.advance": { "total": 2398.5911928430396, "count": 232793, "self": 4.441678980013421, "children": { "env_step": { "total": 1856.7016968720432, "count": 232793, "self": 1565.4650324130466, "children": { "SubprocessEnvManager._take_step": { "total": 288.3901910639248, "count": 232793, "self": 16.52187656777187, "children": { "TorchPolicy.evaluate": { "total": 271.86831449615295, "count": 222894, "self": 271.86831449615295 } } }, "workers": { "total": 2.846473395071598, "count": 232793, "self": 0.0, "children": { "worker_root": { "total": 2399.58553051806, "count": 232793, "is_parallel": true, "self": 1122.8971664021165, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011802279999528764, "count": 1, "is_parallel": true, "self": 0.0003372239999634985, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008430039999893779, "count": 2, "is_parallel": true, "self": 0.0008430039999893779 } } }, "UnityEnvironment.step": { "total": 0.0276234260001047, "count": 1, "is_parallel": true, "self": 0.0003271949999543722, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023324400001456524, "count": 1, "is_parallel": true, "self": 0.00023324400001456524 }, "communicator.exchange": { "total": 0.02632064200008699, "count": 1, "is_parallel": true, "self": 0.02632064200008699 }, "steps_from_proto": { "total": 0.0007423450000487719, "count": 1, "is_parallel": true, "self": 0.00022498900000300637, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005173560000457655, "count": 2, "is_parallel": true, "self": 0.0005173560000457655 } } } } } } }, "UnityEnvironment.step": { "total": 1276.6883641159434, "count": 232792, "is_parallel": true, "self": 38.7146432028826, "children": { "UnityEnvironment._generate_step_input": { "total": 78.12877539697342, "count": 232792, "is_parallel": true, "self": 78.12877539697342 }, "communicator.exchange": { "total": 1066.0530646450118, "count": 232792, "is_parallel": true, "self": 1066.0530646450118 }, "steps_from_proto": { "total": 93.7918808710757, "count": 232792, "is_parallel": true, "self": 34.007357544251136, "children": { "_process_rank_one_or_two_observation": { "total": 59.78452332682457, "count": 465584, "is_parallel": true, "self": 59.78452332682457 } } } } } } } } } } }, "trainer_advance": { "total": 537.447816990983, "count": 232793, "self": 6.627346954905647, "children": { "process_trajectory": { "total": 138.41852042607673, "count": 232793, "self": 136.90458323607743, "children": { "RLTrainer._checkpoint": { "total": 1.5139371899992966, "count": 10, "self": 1.5139371899992966 } } }, "_update_policy": { "total": 392.40194961000066, "count": 97, "self": 331.23154838199264, "children": { "TorchPPOOptimizer.update": { "total": 61.17040122800802, "count": 2910, "self": 61.17040122800802 } } } } } } }, "trainer_threads": { "total": 1.44300020110677e-06, "count": 1, "self": 1.44300020110677e-06 }, "TrainerController._save_models": { "total": 0.19355732699978034, "count": 1, "self": 0.0033212159996764967, "children": { "RLTrainer._checkpoint": { "total": 0.19023611100010385, "count": 1, "self": 0.19023611100010385 } } } } } } }