{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4003045558929443, "min": 1.4003045558929443, "max": 1.4283618927001953, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68409.078125, "min": 68108.203125, "max": 77207.234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 97.62721893491124, "min": 93.02083333333333, "max": 382.08396946564886, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49497.0, "min": 49033.0, "max": 50158.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999993.0, "min": 49620.0, "max": 1999993.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999993.0, "min": 49620.0, "max": 1999993.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.34700083732605, "min": -0.01532189641147852, "max": 2.374598741531372, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1189.929443359375, "min": -1.9918465614318848, "max": 1201.339599609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7202396383417193, "min": 1.8018920790690642, "max": 3.795683827251196, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1886.1614966392517, "min": 234.24597027897835, "max": 1887.087575674057, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7202396383417193, "min": 1.8018920790690642, "max": 3.795683827251196, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1886.1614966392517, "min": 234.24597027897835, "max": 1887.087575674057, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016071515468259655, "min": 0.012876435923196065, "max": 0.019702955783577634, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03214303093651931, "min": 0.02575287184639213, "max": 0.05864017586281989, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05256310521314542, "min": 0.02384381148343285, "max": 0.06123736041287581, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10512621042629083, "min": 0.0476876229668657, "max": 0.1742868531495333, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.455698514800009e-06, "min": 4.455698514800009e-06, "max": 0.00029528737657087494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.911397029600018e-06, "min": 8.911397029600018e-06, "max": 0.0008437150687616499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1014852, "min": 0.1014852, "max": 0.19842912500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.2029704, "min": 0.2029704, "max": 0.5812383500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.411148000000015e-05, "min": 8.411148000000015e-05, "max": 0.0049216133374999985, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001682229600000003, "min": 0.0001682229600000003, "max": 0.014063793665000001, "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": "1716484211", "python_version": "3.10.14 (main, Mar 21 2024, 16:24:04) [GCC 11.2.0]", "command_line_arguments": "/home/raghu/anaconda3/envs/rl/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": "1716485331" }, "total": 1119.3735783930024, "count": 1, "self": 0.2180449010047596, "children": { "run_training.setup": { "total": 0.027685282999300398, "count": 1, "self": 0.027685282999300398 }, "TrainerController.start_learning": { "total": 1119.1278482089983, "count": 1, "self": 2.4193053499075177, "children": { "TrainerController._reset_env": { "total": 1.2940369789976103, "count": 1, "self": 1.2940369789976103 }, "TrainerController.advance": { "total": 1115.3307369180911, "count": 231049, "self": 1.984914125288924, "children": { "env_step": { "total": 894.3482673409744, "count": 231049, "self": 698.6032604182074, "children": { "SubprocessEnvManager._take_step": { "total": 194.1044238987488, "count": 231049, "self": 7.957432907580369, "children": { "TorchPolicy.evaluate": { "total": 186.14699099116842, "count": 222866, "self": 186.14699099116842 } } }, "workers": { "total": 1.6405830240182695, "count": 231049, "self": 0.0, "children": { "worker_root": { "total": 1116.0201048576419, "count": 231049, "is_parallel": true, "self": 544.3001171263313, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007592479996674228, "count": 1, "is_parallel": true, "self": 0.00011948300016229041, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006397649995051324, "count": 2, "is_parallel": true, "self": 0.0006397649995051324 } } }, "UnityEnvironment.step": { "total": 0.014035325999429915, "count": 1, "is_parallel": true, "self": 0.0002480930015735794, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018956399799208157, "count": 1, "is_parallel": true, "self": 0.00018956399799208157 }, "communicator.exchange": { "total": 0.012967361999471905, "count": 1, "is_parallel": true, "self": 0.012967361999471905 }, "steps_from_proto": { "total": 0.0006303070003923494, "count": 1, "is_parallel": true, "self": 0.00026601700301398523, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003642899973783642, "count": 2, "is_parallel": true, "self": 0.0003642899973783642 } } } } } } }, "UnityEnvironment.step": { "total": 571.7199877313105, "count": 231048, "is_parallel": true, "self": 15.01828447819571, "children": { "UnityEnvironment._generate_step_input": { "total": 29.96765741771742, "count": 231048, "is_parallel": true, "self": 29.96765741771742 }, "communicator.exchange": { "total": 493.47698452369514, "count": 231048, "is_parallel": true, "self": 493.47698452369514 }, "steps_from_proto": { "total": 33.25706131170227, "count": 231048, "is_parallel": true, "self": 10.986671726055647, "children": { "_process_rank_one_or_two_observation": { "total": 22.270389585646626, "count": 462096, "is_parallel": true, "self": 22.270389585646626 } } } } } } } } } } }, "trainer_advance": { "total": 218.9975554518278, "count": 231049, "self": 3.546399393977481, "children": { "process_trajectory": { "total": 78.49508976085781, "count": 231049, "self": 77.70367890086345, "children": { "RLTrainer._checkpoint": { "total": 0.7914108599943575, "count": 10, "self": 0.7914108599943575 } } }, "_update_policy": { "total": 136.9560662969925, "count": 96, "self": 107.82921692915625, "children": { "TorchPPOOptimizer.update": { "total": 29.126849367836257, "count": 2880, "self": 29.126849367836257 } } } } } } }, "trainer_threads": { "total": 6.810005288571119e-07, "count": 1, "self": 6.810005288571119e-07 }, "TrainerController._save_models": { "total": 0.08376828100153944, "count": 1, "self": 0.0021573980011453386, "children": { "RLTrainer._checkpoint": { "total": 0.0816108830003941, "count": 1, "self": 0.0816108830003941 } } } } } } }