{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4042212963104248, "min": 1.4042212963104248, "max": 1.4317500591278076, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71408.8671875, "min": 68227.5, "max": 77344.4140625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.50457038391225, "min": 85.86111111111111, "max": 381.09923664122135, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49506.0, "min": 48801.0, "max": 50116.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999956.0, "min": 49798.0, "max": 1999956.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999956.0, "min": 49798.0, "max": 1999956.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3440213203430176, "min": 0.1102542132139206, "max": 2.446491003036499, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1282.1796875, "min": 14.333047866821289, "max": 1389.9285888671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6277055865667855, "min": 1.8946976544765326, "max": 3.8669431615014407, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1984.3549558520317, "min": 246.31069508194923, "max": 2101.6849341392517, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6277055865667855, "min": 1.8946976544765326, "max": 3.8669431615014407, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1984.3549558520317, "min": 246.31069508194923, "max": 2101.6849341392517, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015706201507903948, "min": 0.012965817042034663, "max": 0.020824089848125976, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04711860452371184, "min": 0.026966603120793783, "max": 0.058637344516318995, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05186585850185818, "min": 0.021659691041956343, "max": 0.06616274089448983, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15559757550557454, "min": 0.043319382083912686, "max": 0.19848822268346947, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.561748812783326e-06, "min": 3.561748812783326e-06, "max": 0.00029535510154829995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0685246438349979e-05, "min": 1.0685246438349979e-05, "max": 0.00084394306868565, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118721666666665, "min": 0.10118721666666665, "max": 0.19845170000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30356164999999996, "min": 0.20750915, "max": 0.5813143500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.924211166666658e-05, "min": 6.924211166666658e-05, "max": 0.004922739829999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020772633499999976, "min": 0.00020772633499999976, "max": 0.014067586065000002, "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": "1710210597", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710213180" }, "total": 2582.8102378460003, "count": 1, "self": 0.7499562160005553, "children": { "run_training.setup": { "total": 0.05552854899997328, "count": 1, "self": 0.05552854899997328 }, "TrainerController.start_learning": { "total": 2582.0047530809998, "count": 1, "self": 4.858943993968296, "children": { "TrainerController._reset_env": { "total": 2.6844827019999684, "count": 1, "self": 2.6844827019999684 }, "TrainerController.advance": { "total": 2574.2794418670314, "count": 231821, "self": 4.976632657021128, "children": { "env_step": { "total": 2082.6228499829776, "count": 231821, "self": 1722.7816529082165, "children": { "SubprocessEnvManager._take_step": { "total": 356.6355043598219, "count": 231821, "self": 18.487273338861996, "children": { "TorchPolicy.evaluate": { "total": 338.1482310209599, "count": 223038, "self": 338.1482310209599 } } }, "workers": { "total": 3.2056927149392322, "count": 231821, "self": 0.0, "children": { "worker_root": { "total": 2574.1722805610602, "count": 231821, "is_parallel": true, "self": 1187.601093140027, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009203550000620453, "count": 1, "is_parallel": true, "self": 0.00024617099984425295, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006741840002177923, "count": 2, "is_parallel": true, "self": 0.0006741840002177923 } } }, "UnityEnvironment.step": { "total": 0.03209778300015387, "count": 1, "is_parallel": true, "self": 0.00037865000012970995, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020661099983954045, "count": 1, "is_parallel": true, "self": 0.00020661099983954045 }, "communicator.exchange": { "total": 0.0307055670000409, "count": 1, "is_parallel": true, "self": 0.0307055670000409 }, "steps_from_proto": { "total": 0.0008069550001437165, "count": 1, "is_parallel": true, "self": 0.00021549400003095798, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005914610001127585, "count": 2, "is_parallel": true, "self": 0.0005914610001127585 } } } } } } }, "UnityEnvironment.step": { "total": 1386.5711874210333, "count": 231820, "is_parallel": true, "self": 41.341769665846186, "children": { "UnityEnvironment._generate_step_input": { "total": 91.07358088305546, "count": 231820, "is_parallel": true, "self": 91.07358088305546 }, "communicator.exchange": { "total": 1156.3643932881048, "count": 231820, "is_parallel": true, "self": 1156.3643932881048 }, "steps_from_proto": { "total": 97.79144358402687, "count": 231820, "is_parallel": true, "self": 36.91408799602618, "children": { "_process_rank_one_or_two_observation": { "total": 60.87735558800068, "count": 463640, "is_parallel": true, "self": 60.87735558800068 } } } } } } } } } } }, "trainer_advance": { "total": 486.6799592270329, "count": 231821, "self": 7.427420929013124, "children": { "process_trajectory": { "total": 161.28685871802054, "count": 231821, "self": 159.79075337902054, "children": { "RLTrainer._checkpoint": { "total": 1.496105338999996, "count": 10, "self": 1.496105338999996 } } }, "_update_policy": { "total": 317.96567957999923, "count": 97, "self": 254.2705495060004, "children": { "TorchPPOOptimizer.update": { "total": 63.695130073998826, "count": 2910, "self": 63.695130073998826 } } } } } } }, "trainer_threads": { "total": 1.220000285684364e-06, "count": 1, "self": 1.220000285684364e-06 }, "TrainerController._save_models": { "total": 0.1818832979997751, "count": 1, "self": 0.0033330819996990613, "children": { "RLTrainer._checkpoint": { "total": 0.17855021600007603, "count": 1, "self": 0.17855021600007603 } } } } } } }