{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.402669906616211, "min": 1.402669906616211, "max": 1.4265022277832031, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69443.3828125, "min": 67718.7265625, "max": 79473.0, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 103.66525423728814, "min": 87.17491166077738, "max": 392.9685039370079, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48930.0, "min": 48855.0, "max": 50078.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999980.0, "min": 49368.0, "max": 1999980.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999980.0, "min": 49368.0, "max": 1999980.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3273210525512695, "min": 0.08333880454301834, "max": 2.4460620880126953, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1098.4954833984375, "min": 10.500689506530762, "max": 1350.4368896484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.545127571765649, "min": 1.8064893009880232, "max": 3.9783428779916266, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1673.3002138733864, "min": 227.61765192449093, "max": 2165.2409418821335, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.545127571765649, "min": 1.8064893009880232, "max": 3.9783428779916266, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1673.3002138733864, "min": 227.61765192449093, "max": 2165.2409418821335, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014592017988777822, "min": 0.012267607592366402, "max": 0.019799958011976235, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04377605396633347, "min": 0.024535215184732805, "max": 0.05939987403592871, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.046377381061514227, "min": 0.02069087317213416, "max": 0.05797531430919965, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.13913214318454267, "min": 0.04138174634426832, "max": 0.1714813775072495, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6152987949333295e-06, "min": 3.6152987949333295e-06, "max": 0.000295359976546675, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0845896384799988e-05, "min": 1.0845896384799988e-05, "max": 0.0008441116686294499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120506666666666, "min": 0.10120506666666666, "max": 0.198453325, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036152, "min": 0.20754425000000004, "max": 0.58137055, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.01328266666666e-05, "min": 7.01328266666666e-05, "max": 0.004922820917500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021039847999999978, "min": 0.00021039847999999978, "max": 0.014070390445, "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": "1678270765", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678273350" }, "total": 2584.658673856, "count": 1, "self": 0.44479924799998116, "children": { "run_training.setup": { "total": 0.11207445800005189, "count": 1, "self": 0.11207445800005189 }, "TrainerController.start_learning": { "total": 2584.1018001499997, "count": 1, "self": 4.6185044011085665, "children": { "TrainerController._reset_env": { "total": 9.443798042000026, "count": 1, "self": 9.443798042000026 }, "TrainerController.advance": { "total": 2569.924823888891, "count": 232167, "self": 5.143489133814455, "children": { "env_step": { "total": 2005.542078685045, "count": 232167, "self": 1672.757015552945, "children": { "SubprocessEnvManager._take_step": { "total": 329.71666865308475, "count": 232167, "self": 17.43242432013085, "children": { "TorchPolicy.evaluate": { "total": 312.2842443329539, "count": 223024, "self": 77.2320422010664, "children": { "TorchPolicy.sample_actions": { "total": 235.0522021318875, "count": 223024, "self": 235.0522021318875 } } } } }, "workers": { "total": 3.0683944790152964, "count": 232167, "self": 0.0, "children": { "worker_root": { "total": 2574.9174379957967, "count": 232167, "is_parallel": true, "self": 1220.7829908347658, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009875540001758054, "count": 1, "is_parallel": true, "self": 0.0003796850000981067, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006078690000776987, "count": 2, "is_parallel": true, "self": 0.0006078690000776987 } } }, "UnityEnvironment.step": { "total": 0.07387464399994315, "count": 1, "is_parallel": true, "self": 0.00036667999961537134, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022085400019022927, "count": 1, "is_parallel": true, "self": 0.00022085400019022927 }, "communicator.exchange": { "total": 0.07083684300005189, "count": 1, "is_parallel": true, "self": 0.07083684300005189 }, "steps_from_proto": { "total": 0.0024502670000856597, "count": 1, "is_parallel": true, "self": 0.0002941010000085953, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021561660000770644, "count": 2, "is_parallel": true, "self": 0.0021561660000770644 } } } } } } }, "UnityEnvironment.step": { "total": 1354.134447161031, "count": 232166, "is_parallel": true, "self": 40.21728005491741, "children": { "UnityEnvironment._generate_step_input": { "total": 86.32860143607763, "count": 232166, "is_parallel": true, "self": 86.32860143607763 }, "communicator.exchange": { "total": 1129.911195797001, "count": 232166, "is_parallel": true, "self": 1129.911195797001 }, "steps_from_proto": { "total": 97.67736987303488, "count": 232166, "is_parallel": true, "self": 42.123816325133475, "children": { "_process_rank_one_or_two_observation": { "total": 55.5535535479014, "count": 464332, "is_parallel": true, "self": 55.5535535479014 } } } } } } } } } } }, "trainer_advance": { "total": 559.2392560700314, "count": 232167, "self": 7.127967008024825, "children": { "process_trajectory": { "total": 177.01906942600544, "count": 232167, "self": 175.85898210100504, "children": { "RLTrainer._checkpoint": { "total": 1.1600873250004042, "count": 10, "self": 1.1600873250004042 } } }, "_update_policy": { "total": 375.0922196360011, "count": 97, "self": 315.57464162398946, "children": { "TorchPPOOptimizer.update": { "total": 59.517578012011654, "count": 2910, "self": 59.517578012011654 } } } } } } }, "trainer_threads": { "total": 9.37000095291296e-07, "count": 1, "self": 9.37000095291296e-07 }, "TrainerController._save_models": { "total": 0.11467288099993311, "count": 1, "self": 0.002163785999528045, "children": { "RLTrainer._checkpoint": { "total": 0.11250909500040507, "count": 1, "self": 0.11250909500040507 } } } } } } }