{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.402338981628418, "min": 1.402338981628418, "max": 1.4278053045272827, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70630.203125, "min": 68976.21875, "max": 76460.8046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 79.88511326860842, "min": 78.55414012738854, "max": 369.7851851851852, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49369.0, "min": 49011.0, "max": 50178.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999977.0, "min": 49652.0, "max": 1999977.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999977.0, "min": 49652.0, "max": 1999977.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.462183952331543, "min": 0.09756673127412796, "max": 2.480609655380249, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1521.629638671875, "min": 13.073942184448242, "max": 1533.27880859375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9522961083932215, "min": 1.886446245570681, "max": 4.0357692395385945, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2442.518994987011, "min": 252.78379690647125, "max": 2442.518994987011, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9522961083932215, "min": 1.886446245570681, "max": 4.0357692395385945, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2442.518994987011, "min": 252.78379690647125, "max": 2442.518994987011, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019417383357358632, "min": 0.014330837083010313, "max": 0.020690503374983866, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.058252150072075896, "min": 0.028661674166020626, "max": 0.061171658015518916, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06530264197952217, "min": 0.020861603661129872, "max": 0.06530264197952217, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1959079259385665, "min": 0.041723207322259745, "max": 0.1959079259385665, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4615988461666612e-06, "min": 3.4615988461666612e-06, "max": 0.0002953806015397999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0384796538499983e-05, "min": 1.0384796538499983e-05, "max": 0.0008443776185408, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10115383333333333, "min": 0.10115383333333333, "max": 0.19846019999999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034615, "min": 0.20746710000000002, "max": 0.5814592000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.757628333333325e-05, "min": 6.757628333333325e-05, "max": 0.004923163980000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020272884999999978, "min": 0.00020272884999999978, "max": 0.014074814080000001, "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": "1685278071", "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": "1685281117" }, "total": 3046.396669998, "count": 1, "self": 0.4949251319999348, "children": { "run_training.setup": { "total": 0.04660643400001163, "count": 1, "self": 0.04660643400001163 }, "TrainerController.start_learning": { "total": 3045.8551384320003, "count": 1, "self": 6.144664375987304, "children": { "TrainerController._reset_env": { "total": 4.156479524000019, "count": 1, "self": 4.156479524000019 }, "TrainerController.advance": { "total": 3035.422140965013, "count": 232094, "self": 6.069808721008485, "children": { "env_step": { "total": 2357.0173465329144, "count": 232094, "self": 1980.5619013780652, "children": { "SubprocessEnvManager._take_step": { "total": 372.22706136690385, "count": 232094, "self": 21.774220741925433, "children": { "TorchPolicy.evaluate": { "total": 350.4528406249784, "count": 222876, "self": 350.4528406249784 } } }, "workers": { "total": 4.228383787945461, "count": 232094, "self": 0.0, "children": { "worker_root": { "total": 3035.480709730047, "count": 232094, "is_parallel": true, "self": 1431.2468122680748, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001085232999969321, "count": 1, "is_parallel": true, "self": 0.0003112709999868457, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007739619999824754, "count": 2, "is_parallel": true, "self": 0.0007739619999824754 } } }, "UnityEnvironment.step": { "total": 0.03748053499998605, "count": 1, "is_parallel": true, "self": 0.0003907459999368257, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002613600000245242, "count": 1, "is_parallel": true, "self": 0.0002613600000245242 }, "communicator.exchange": { "total": 0.03596000500004948, "count": 1, "is_parallel": true, "self": 0.03596000500004948 }, "steps_from_proto": { "total": 0.0008684239999752208, "count": 1, "is_parallel": true, "self": 0.00025312399998256296, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006152999999926578, "count": 2, "is_parallel": true, "self": 0.0006152999999926578 } } } } } } }, "UnityEnvironment.step": { "total": 1604.233897461972, "count": 232093, "is_parallel": true, "self": 47.27397735105774, "children": { "UnityEnvironment._generate_step_input": { "total": 96.66756759494598, "count": 232093, "is_parallel": true, "self": 96.66756759494598 }, "communicator.exchange": { "total": 1341.3030087309967, "count": 232093, "is_parallel": true, "self": 1341.3030087309967 }, "steps_from_proto": { "total": 118.98934378497171, "count": 232093, "is_parallel": true, "self": 44.168638341821406, "children": { "_process_rank_one_or_two_observation": { "total": 74.8207054431503, "count": 464186, "is_parallel": true, "self": 74.8207054431503 } } } } } } } } } } }, "trainer_advance": { "total": 672.3349857110901, "count": 232094, "self": 9.188162929976897, "children": { "process_trajectory": { "total": 163.40061744411395, "count": 232094, "self": 161.8595589701137, "children": { "RLTrainer._checkpoint": { "total": 1.5410584740002378, "count": 10, "self": 1.5410584740002378 } } }, "_update_policy": { "total": 499.74620533699925, "count": 97, "self": 429.7221016310144, "children": { "TorchPPOOptimizer.update": { "total": 70.02410370598483, "count": 2910, "self": 70.02410370598483 } } } } } } }, "trainer_threads": { "total": 1.1319998520775698e-06, "count": 1, "self": 1.1319998520775698e-06 }, "TrainerController._save_models": { "total": 0.13185243499992794, "count": 1, "self": 0.002100609999615699, "children": { "RLTrainer._checkpoint": { "total": 0.12975182500031224, "count": 1, "self": 0.12975182500031224 } } } } } } }