{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405992031097412, "min": 1.405992031097412, "max": 1.4267644882202148, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69070.765625, "min": 68678.2578125, "max": 78185.5546875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 98.0118811881188, "min": 85.79549393414212, "max": 398.91269841269843, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49496.0, "min": 48767.0, "max": 50263.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999953.0, "min": 49939.0, "max": 1999953.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999953.0, "min": 49939.0, "max": 1999953.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.452741861343384, "min": 0.14861877262592316, "max": 2.464822769165039, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1238.6346435546875, "min": 18.577346801757812, "max": 1388.2587890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.835281258644444, "min": 1.7310796666145325, "max": 3.9568186052654624, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1936.8170356154442, "min": 216.38495832681656, "max": 2192.077507317066, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.835281258644444, "min": 1.7310796666145325, "max": 3.9568186052654624, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1936.8170356154442, "min": 216.38495832681656, "max": 2192.077507317066, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015015074141976786, "min": 0.0134735712924036, "max": 0.021555641595235403, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.045045222425930356, "min": 0.0269471425848072, "max": 0.05768268390323404, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04700063665707906, "min": 0.020475303350637356, "max": 0.060542584003673655, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14100190997123718, "min": 0.04095060670127471, "max": 0.18162775201102097, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.350748883116666e-06, "min": 3.350748883116666e-06, "max": 0.00029533395155535, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0052246649349998e-05, "min": 1.0052246649349998e-05, "max": 0.0008439852186715998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111688333333334, "min": 0.10111688333333334, "max": 0.19844465, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30335065, "min": 0.20739964999999994, "max": 0.5813284000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.573247833333334e-05, "min": 6.573247833333334e-05, "max": 0.004922388035000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.000197197435, "min": 0.000197197435, "max": 0.014068287159999998, "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": "1717486868", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717489306" }, "total": 2437.651747253, "count": 1, "self": 0.49676496599977327, "children": { "run_training.setup": { "total": 0.05820327099991118, "count": 1, "self": 0.05820327099991118 }, "TrainerController.start_learning": { "total": 2437.0967790160003, "count": 1, "self": 4.501182706123927, "children": { "TrainerController._reset_env": { "total": 3.3064272919999667, "count": 1, "self": 3.3064272919999667 }, "TrainerController.advance": { "total": 2429.171990724876, "count": 232295, "self": 4.773534662987458, "children": { "env_step": { "total": 1931.029950685995, "count": 232295, "self": 1597.5895898390218, "children": { "SubprocessEnvManager._take_step": { "total": 330.63937088190414, "count": 232295, "self": 16.863983799913058, "children": { "TorchPolicy.evaluate": { "total": 313.7753870819911, "count": 222934, "self": 313.7753870819911 } } }, "workers": { "total": 2.8009899650688794, "count": 232295, "self": 0.0, "children": { "worker_root": { "total": 2430.0175083319696, "count": 232295, "is_parallel": true, "self": 1139.3075557039856, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008543180000515349, "count": 1, "is_parallel": true, "self": 0.0002057100001593426, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006486079998921923, "count": 2, "is_parallel": true, "self": 0.0006486079998921923 } } }, "UnityEnvironment.step": { "total": 0.02865306099999998, "count": 1, "is_parallel": true, "self": 0.0003757799998993505, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020405200007189706, "count": 1, "is_parallel": true, "self": 0.00020405200007189706 }, "communicator.exchange": { "total": 0.02730650900002729, "count": 1, "is_parallel": true, "self": 0.02730650900002729 }, "steps_from_proto": { "total": 0.0007667200000014418, "count": 1, "is_parallel": true, "self": 0.00019449000001259265, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005722299999888492, "count": 2, "is_parallel": true, "self": 0.0005722299999888492 } } } } } } }, "UnityEnvironment.step": { "total": 1290.709952627984, "count": 232294, "is_parallel": true, "self": 38.99744965990408, "children": { "UnityEnvironment._generate_step_input": { "total": 81.57357351798908, "count": 232294, "is_parallel": true, "self": 81.57357351798908 }, "communicator.exchange": { "total": 1079.4368664450412, "count": 232294, "is_parallel": true, "self": 1079.4368664450412 }, "steps_from_proto": { "total": 90.70206300504947, "count": 232294, "is_parallel": true, "self": 32.3762698411972, "children": { "_process_rank_one_or_two_observation": { "total": 58.32579316385227, "count": 464588, "is_parallel": true, "self": 58.32579316385227 } } } } } } } } } } }, "trainer_advance": { "total": 493.36850537589385, "count": 232295, "self": 6.668735541909086, "children": { "process_trajectory": { "total": 155.42855173398448, "count": 232295, "self": 154.11817262298416, "children": { "RLTrainer._checkpoint": { "total": 1.3103791110003158, "count": 10, "self": 1.3103791110003158 } } }, "_update_policy": { "total": 331.2712181000003, "count": 97, "self": 267.3497125760008, "children": { "TorchPPOOptimizer.update": { "total": 63.921505523999485, "count": 2910, "self": 63.921505523999485 } } } } } } }, "trainer_threads": { "total": 1.0859998837986495e-06, "count": 1, "self": 1.0859998837986495e-06 }, "TrainerController._save_models": { "total": 0.11717720700016798, "count": 1, "self": 0.0021927410002717806, "children": { "RLTrainer._checkpoint": { "total": 0.1149844659998962, "count": 1, "self": 0.1149844659998962 } } } } } } }