{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4054383039474487, "min": 1.4054383039474487, "max": 1.4280701875686646, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69141.9453125, "min": 68368.953125, "max": 77523.46875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 98.08514851485148, "min": 87.34159292035399, "max": 389.6821705426357, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49533.0, "min": 48852.0, "max": 50269.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999920.0, "min": 49899.0, "max": 1999920.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999920.0, "min": 49899.0, "max": 1999920.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4514474868774414, "min": 0.022020261734724045, "max": 2.4514474868774414, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1237.98095703125, "min": 2.8185935020446777, "max": 1367.6392822265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8464091450861186, "min": 1.8417077888734639, "max": 4.033162442763113, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1942.4366182684898, "min": 235.73859697580338, "max": 2160.5472719073296, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8464091450861186, "min": 1.8417077888734639, "max": 4.033162442763113, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1942.4366182684898, "min": 235.73859697580338, "max": 2160.5472719073296, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01650063612388395, "min": 0.013148204148617676, "max": 0.018952806592763712, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04950190837165185, "min": 0.026334485578505942, "max": 0.05541133160877508, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.049755815333790254, "min": 0.02162509942427278, "max": 0.06937589020364814, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14926744600137076, "min": 0.04325019884854556, "max": 0.20812767061094442, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.274498908533343e-06, "min": 3.274498908533343e-06, "max": 0.0002952844515718499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.82349672560003e-06, "min": 9.82349672560003e-06, "max": 0.00084407476864175, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10109146666666669, "min": 0.10109146666666669, "max": 0.19842814999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30327440000000006, "min": 0.20735780000000004, "max": 0.5813582500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.446418666666685e-05, "min": 6.446418666666685e-05, "max": 0.004921564685000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019339256000000055, "min": 0.00019339256000000055, "max": 0.014069776675, "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": "1687335961", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687338455" }, "total": 2494.294788411, "count": 1, "self": 0.4455537579997326, "children": { "run_training.setup": { "total": 0.04328332800002954, "count": 1, "self": 0.04328332800002954 }, "TrainerController.start_learning": { "total": 2493.805951325, "count": 1, "self": 4.42682555394822, "children": { "TrainerController._reset_env": { "total": 5.696444506999967, "count": 1, "self": 5.696444506999967 }, "TrainerController.advance": { "total": 2483.5545508580517, "count": 231988, "self": 4.642258775174469, "children": { "env_step": { "total": 1942.5800154899616, "count": 231988, "self": 1633.2912133178356, "children": { "SubprocessEnvManager._take_step": { "total": 306.45630932503667, "count": 231988, "self": 17.430387148999955, "children": { "TorchPolicy.evaluate": { "total": 289.0259221760367, "count": 222913, "self": 289.0259221760367 } } }, "workers": { "total": 2.8324928470893838, "count": 231988, "self": 0.0, "children": { "worker_root": { "total": 2485.818742864026, "count": 231988, "is_parallel": true, "self": 1148.166850272006, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009645800000157578, "count": 1, "is_parallel": true, "self": 0.0003109820000304353, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006535979999853225, "count": 2, "is_parallel": true, "self": 0.0006535979999853225 } } }, "UnityEnvironment.step": { "total": 0.03077722000000449, "count": 1, "is_parallel": true, "self": 0.0003392969999822526, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021333500001219363, "count": 1, "is_parallel": true, "self": 0.00021333500001219363 }, "communicator.exchange": { "total": 0.029490681000027053, "count": 1, "is_parallel": true, "self": 0.029490681000027053 }, "steps_from_proto": { "total": 0.0007339069999829917, "count": 1, "is_parallel": true, "self": 0.00022689099995432116, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005070160000286705, "count": 2, "is_parallel": true, "self": 0.0005070160000286705 } } } } } } }, "UnityEnvironment.step": { "total": 1337.6518925920197, "count": 231987, "is_parallel": true, "self": 40.19379023199281, "children": { "UnityEnvironment._generate_step_input": { "total": 85.47652694603221, "count": 231987, "is_parallel": true, "self": 85.47652694603221 }, "communicator.exchange": { "total": 1113.0158211250057, "count": 231987, "is_parallel": true, "self": 1113.0158211250057 }, "steps_from_proto": { "total": 98.96575428898905, "count": 231987, "is_parallel": true, "self": 37.88391167194658, "children": { "_process_rank_one_or_two_observation": { "total": 61.08184261704247, "count": 463974, "is_parallel": true, "self": 61.08184261704247 } } } } } } } } } } }, "trainer_advance": { "total": 536.3322765929156, "count": 231988, "self": 6.7831721159057, "children": { "process_trajectory": { "total": 140.11433661400872, "count": 231988, "self": 138.79520050300903, "children": { "RLTrainer._checkpoint": { "total": 1.3191361109996933, "count": 10, "self": 1.3191361109996933 } } }, "_update_policy": { "total": 389.4347678630012, "count": 97, "self": 328.49863377100843, "children": { "TorchPPOOptimizer.update": { "total": 60.936134091992756, "count": 2910, "self": 60.936134091992756 } } } } } } }, "trainer_threads": { "total": 1.154000074166106e-06, "count": 1, "self": 1.154000074166106e-06 }, "TrainerController._save_models": { "total": 0.12812925200023528, "count": 1, "self": 0.0023870720001468726, "children": { "RLTrainer._checkpoint": { "total": 0.1257421800000884, "count": 1, "self": 0.1257421800000884 } } } } } } }