{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4114900827407837, "min": 1.4114900827407837, "max": 1.4288949966430664, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69946.390625, "min": 67747.65625, "max": 75902.890625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 87.93416370106762, "min": 79.73870967741935, "max": 395.9761904761905, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49419.0, "min": 49323.0, "max": 50272.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999933.0, "min": 49869.0, "max": 1999933.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999933.0, "min": 49869.0, "max": 1999933.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3731133937835693, "min": 0.04791467264294624, "max": 2.4894790649414062, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1333.689697265625, "min": 5.9893341064453125, "max": 1503.6484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.494483122197759, "min": 1.842660560965538, "max": 3.9283764176359472, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1963.8995146751404, "min": 230.33257012069225, "max": 2350.098907470703, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.494483122197759, "min": 1.842660560965538, "max": 3.9283764176359472, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1963.8995146751404, "min": 230.33257012069225, "max": 2350.098907470703, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016794073615488337, "min": 0.012548490201637227, "max": 0.019206742162350566, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050382220846465015, "min": 0.025096980403274453, "max": 0.05752035505429376, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05425964701506827, "min": 0.022553753449271123, "max": 0.06067276224493981, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1627789410452048, "min": 0.045107506898542246, "max": 0.17031827755272388, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6471987843000036e-06, "min": 3.6471987843000036e-06, "max": 0.00029528887657037493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.094159635290001e-05, "min": 1.094159635290001e-05, "max": 0.0008440597686467501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012157, "min": 0.1012157, "max": 0.19842962500000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036471, "min": 0.20758715000000005, "max": 0.5813532499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.066343000000005e-05, "min": 7.066343000000005e-05, "max": 0.0049216382875, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021199029000000018, "min": 0.00021199029000000018, "max": 0.014069527174999999, "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": "1701264279", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701266695" }, "total": 2416.280166155, "count": 1, "self": 0.7914687380007308, "children": { "run_training.setup": { "total": 0.05575443600002927, "count": 1, "self": 0.05575443600002927 }, "TrainerController.start_learning": { "total": 2415.4329429809995, "count": 1, "self": 4.62210269490879, "children": { "TrainerController._reset_env": { "total": 3.636980144000063, "count": 1, "self": 3.636980144000063 }, "TrainerController.advance": { "total": 2407.021637638091, "count": 232596, "self": 4.8806311481394005, "children": { "env_step": { "total": 1899.8684634209633, "count": 232596, "self": 1571.4212151411016, "children": { "SubprocessEnvManager._take_step": { "total": 325.66109965892167, "count": 232596, "self": 17.251392621919194, "children": { "TorchPolicy.evaluate": { "total": 308.4097070370025, "count": 222941, "self": 308.4097070370025 } } }, "workers": { "total": 2.786148620939912, "count": 232596, "self": 0.0, "children": { "worker_root": { "total": 2407.6550479798316, "count": 232596, "is_parallel": true, "self": 1133.0208548489327, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008171449999281322, "count": 1, "is_parallel": true, "self": 0.00023694300000443036, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005802019999237018, "count": 2, "is_parallel": true, "self": 0.0005802019999237018 } } }, "UnityEnvironment.step": { "total": 0.02878482799997073, "count": 1, "is_parallel": true, "self": 0.00029235499982860347, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019512900007612188, "count": 1, "is_parallel": true, "self": 0.00019512900007612188 }, "communicator.exchange": { "total": 0.027609950000055505, "count": 1, "is_parallel": true, "self": 0.027609950000055505 }, "steps_from_proto": { "total": 0.0006873940000104994, "count": 1, "is_parallel": true, "self": 0.00018451599999025348, "children": { "_process_rank_one_or_two_observation": { "total": 0.000502878000020246, "count": 2, "is_parallel": true, "self": 0.000502878000020246 } } } } } } }, "UnityEnvironment.step": { "total": 1274.634193130899, "count": 232595, "is_parallel": true, "self": 40.18923324387447, "children": { "UnityEnvironment._generate_step_input": { "total": 82.47958439094339, "count": 232595, "is_parallel": true, "self": 82.47958439094339 }, "communicator.exchange": { "total": 1062.8924278010027, "count": 232595, "is_parallel": true, "self": 1062.8924278010027 }, "steps_from_proto": { "total": 89.07294769507848, "count": 232595, "is_parallel": true, "self": 30.944946227074865, "children": { "_process_rank_one_or_two_observation": { "total": 58.12800146800362, "count": 465190, "is_parallel": true, "self": 58.12800146800362 } } } } } } } } } } }, "trainer_advance": { "total": 502.27254306898806, "count": 232596, "self": 6.775565704958922, "children": { "process_trajectory": { "total": 156.20385621602964, "count": 232596, "self": 155.04321616902973, "children": { "RLTrainer._checkpoint": { "total": 1.1606400469999016, "count": 10, "self": 1.1606400469999016 } } }, "_update_policy": { "total": 339.2931211479995, "count": 97, "self": 275.3012053649926, "children": { "TorchPPOOptimizer.update": { "total": 63.9919157830069, "count": 2910, "self": 63.9919157830069 } } } } } } }, "trainer_threads": { "total": 1.433999841538025e-06, "count": 1, "self": 1.433999841538025e-06 }, "TrainerController._save_models": { "total": 0.15222106999999596, "count": 1, "self": 0.00246048899998641, "children": { "RLTrainer._checkpoint": { "total": 0.14976058100000955, "count": 1, "self": 0.14976058100000955 } } } } } } }