{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4042478799819946, "min": 1.4042478799819946, "max": 1.425980567932129, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69663.3359375, "min": 67513.328125, "max": 76349.5625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.21942446043165, "min": 78.44992050874404, "max": 400.424, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49050.0, "min": 48842.0, "max": 50071.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999990.0, "min": 49538.0, "max": 1999990.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999990.0, "min": 49538.0, "max": 1999990.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.447281837463379, "min": 0.025695649906992912, "max": 2.5372462272644043, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1360.688720703125, "min": 3.18626070022583, "max": 1554.9010009765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.773182193259541, "min": 1.8520825952291489, "max": 4.024492117767459, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2097.889299452305, "min": 229.65824180841446, "max": 2450.9156997203827, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.773182193259541, "min": 1.8520825952291489, "max": 4.024492117767459, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2097.889299452305, "min": 229.65824180841446, "max": 2450.9156997203827, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015080716383898915, "min": 0.01448974387738215, "max": 0.020287011452859993, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04524214915169675, "min": 0.029623171131728063, "max": 0.06086103435857998, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05598335050874287, "min": 0.02254077590381106, "max": 0.06075451200207074, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1679500515262286, "min": 0.04508155180762212, "max": 0.1798377410819133, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.8130487290166707e-06, "min": 3.8130487290166707e-06, "max": 0.000295317226560925, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1439146187050012e-05, "min": 1.1439146187050012e-05, "max": 0.0008441976186007998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127098333333336, "min": 0.10127098333333336, "max": 0.19843907500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3038129500000001, "min": 0.20767315000000003, "max": 0.5813992, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.342206833333339e-05, "min": 7.342206833333339e-05, "max": 0.004922109842500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022026620500000018, "min": 0.00022026620500000018, "max": 0.014071820080000004, "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": "1673339911", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673342092" }, "total": 2181.166391285, "count": 1, "self": 0.3892307150003944, "children": { "run_training.setup": { "total": 0.10566819899997881, "count": 1, "self": 0.10566819899997881 }, "TrainerController.start_learning": { "total": 2180.6714923709997, "count": 1, "self": 3.724941298981321, "children": { "TrainerController._reset_env": { "total": 7.36774900599994, "count": 1, "self": 7.36774900599994 }, "TrainerController.advance": { "total": 2169.454374819018, "count": 233079, "self": 3.9473523728252076, "children": { "env_step": { "total": 1703.0049505130914, "count": 233079, "self": 1430.9249859780693, "children": { "SubprocessEnvManager._take_step": { "total": 269.60442605303183, "count": 233079, "self": 13.965629689035836, "children": { "TorchPolicy.evaluate": { "total": 255.638796363996, "count": 222954, "self": 64.59134923909585, "children": { "TorchPolicy.sample_actions": { "total": 191.04744712490015, "count": 222954, "self": 191.04744712490015 } } } } }, "workers": { "total": 2.475538481990384, "count": 233079, "self": 0.0, "children": { "worker_root": { "total": 2173.0696061969907, "count": 233079, "is_parallel": true, "self": 994.0661345670808, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020750209999960134, "count": 1, "is_parallel": true, "self": 0.0003132800000003044, "children": { "_process_rank_one_or_two_observation": { "total": 0.001761740999995709, "count": 2, "is_parallel": true, "self": 0.001761740999995709 } } }, "UnityEnvironment.step": { "total": 0.02677217500001916, "count": 1, "is_parallel": true, "self": 0.0002853189998859307, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002002070000344247, "count": 1, "is_parallel": true, "self": 0.0002002070000344247 }, "communicator.exchange": { "total": 0.025608613000031255, "count": 1, "is_parallel": true, "self": 0.025608613000031255 }, "steps_from_proto": { "total": 0.00067803600006755, "count": 1, "is_parallel": true, "self": 0.00022627400005603704, "children": { "_process_rank_one_or_two_observation": { "total": 0.000451762000011513, "count": 2, "is_parallel": true, "self": 0.000451762000011513 } } } } } } }, "UnityEnvironment.step": { "total": 1179.0034716299099, "count": 233078, "is_parallel": true, "self": 34.0772023279776, "children": { "UnityEnvironment._generate_step_input": { "total": 76.03869257399344, "count": 233078, "is_parallel": true, "self": 76.03869257399344 }, "communicator.exchange": { "total": 977.3621011999588, "count": 233078, "is_parallel": true, "self": 977.3621011999588 }, "steps_from_proto": { "total": 91.52547552798, "count": 233078, "is_parallel": true, "self": 37.76106898913372, "children": { "_process_rank_one_or_two_observation": { "total": 53.76440653884629, "count": 466156, "is_parallel": true, "self": 53.76440653884629 } } } } } } } } } } }, "trainer_advance": { "total": 462.5020719331013, "count": 233079, "self": 5.8266957150663075, "children": { "process_trajectory": { "total": 147.11544563603547, "count": 233079, "self": 145.80312004703546, "children": { "RLTrainer._checkpoint": { "total": 1.312325589000011, "count": 10, "self": 1.312325589000011 } } }, "_update_policy": { "total": 309.55993058199954, "count": 97, "self": 257.0280057629918, "children": { "TorchPPOOptimizer.update": { "total": 52.53192481900771, "count": 2910, "self": 52.53192481900771 } } } } } } }, "trainer_threads": { "total": 8.050001270021312e-07, "count": 1, "self": 8.050001270021312e-07 }, "TrainerController._save_models": { "total": 0.12442644200018549, "count": 1, "self": 0.0019689910000124655, "children": { "RLTrainer._checkpoint": { "total": 0.12245745100017302, "count": 1, "self": 0.12245745100017302 } } } } } } }