{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.407869815826416, "min": 1.407869815826416, "max": 1.4265393018722534, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70753.90625, "min": 69450.8828125, "max": 76050.546875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 93.59848484848484, "min": 77.78582677165355, "max": 389.875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49420.0, "min": 49266.0, "max": 50143.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999970.0, "min": 49823.0, "max": 1999970.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999970.0, "min": 49823.0, "max": 1999970.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.437657117843628, "min": 0.04850928112864494, "max": 2.47505784034729, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1287.0830078125, "min": 6.160678863525391, "max": 1529.36865234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.722964313219894, "min": 1.7902840810028586, "max": 3.916819179058075, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1965.725157380104, "min": 227.36607828736305, "max": 2427.0636330246925, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.722964313219894, "min": 1.7902840810028586, "max": 3.916819179058075, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1965.725157380104, "min": 227.36607828736305, "max": 2427.0636330246925, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016721599680022334, "min": 0.012714983720858677, "max": 0.020466300013746754, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050164799040067, "min": 0.027761302406239943, "max": 0.05846165645731768, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.055136829242110254, "min": 0.02189748411377271, "max": 0.05811110238234202, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16541048772633077, "min": 0.04379496822754542, "max": 0.17024877617756526, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.853248715616661e-06, "min": 3.853248715616661e-06, "max": 0.0002953709265430249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1559746146849983e-05, "min": 1.1559746146849983e-05, "max": 0.0008442138185954, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10128438333333334, "min": 0.10128438333333334, "max": 0.19845697500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30385315, "min": 0.20776549999999996, "max": 0.5814046, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.409072833333322e-05, "min": 7.409072833333322e-05, "max": 0.004923003052500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022227218499999967, "min": 0.00022227218499999967, "max": 0.01407208954, "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": "1671708178", "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": "1671710510" }, "total": 2332.014685921, "count": 1, "self": 0.3831058920000032, "children": { "run_training.setup": { "total": 0.12697928000000047, "count": 1, "self": 0.12697928000000047 }, "TrainerController.start_learning": { "total": 2331.504600749, "count": 1, "self": 4.1513003689783545, "children": { "TrainerController._reset_env": { "total": 7.176792053999975, "count": 1, "self": 7.176792053999975 }, "TrainerController.advance": { "total": 2320.0621033270218, "count": 232849, "self": 4.370364315036113, "children": { "env_step": { "total": 1838.072958746035, "count": 232849, "self": 1546.0973987650482, "children": { "SubprocessEnvManager._take_step": { "total": 289.19850539898744, "count": 232849, "self": 15.11978772186444, "children": { "TorchPolicy.evaluate": { "total": 274.078717677123, "count": 223035, "self": 67.80950885506059, "children": { "TorchPolicy.sample_actions": { "total": 206.2692088220624, "count": 223035, "self": 206.2692088220624 } } } } }, "workers": { "total": 2.7770545819994368, "count": 232849, "self": 0.0, "children": { "worker_root": { "total": 2323.4273593320745, "count": 232849, "is_parallel": true, "self": 1051.0722172812075, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002116997999905834, "count": 1, "is_parallel": true, "self": 0.0003279799999518218, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017890179999540123, "count": 2, "is_parallel": true, "self": 0.0017890179999540123 } } }, "UnityEnvironment.step": { "total": 0.028686829999969632, "count": 1, "is_parallel": true, "self": 0.0003155329999344758, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002056120000588635, "count": 1, "is_parallel": true, "self": 0.0002056120000588635 }, "communicator.exchange": { "total": 0.027366318999952455, "count": 1, "is_parallel": true, "self": 0.027366318999952455 }, "steps_from_proto": { "total": 0.0007993660000238378, "count": 1, "is_parallel": true, "self": 0.00028212500001245644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005172410000113814, "count": 2, "is_parallel": true, "self": 0.0005172410000113814 } } } } } } }, "UnityEnvironment.step": { "total": 1272.355142050867, "count": 232848, "is_parallel": true, "self": 35.8458943797275, "children": { "UnityEnvironment._generate_step_input": { "total": 82.41339243016739, "count": 232848, "is_parallel": true, "self": 82.41339243016739 }, "communicator.exchange": { "total": 1055.3638407149533, "count": 232848, "is_parallel": true, "self": 1055.3638407149533 }, "steps_from_proto": { "total": 98.73201452601893, "count": 232848, "is_parallel": true, "self": 43.30700306499398, "children": { "_process_rank_one_or_two_observation": { "total": 55.42501146102495, "count": 465696, "is_parallel": true, "self": 55.42501146102495 } } } } } } } } } } }, "trainer_advance": { "total": 477.6187802659505, "count": 232849, "self": 6.46728056882273, "children": { "process_trajectory": { "total": 156.55128344412776, "count": 232849, "self": 155.37826330512826, "children": { "RLTrainer._checkpoint": { "total": 1.1730201389995045, "count": 10, "self": 1.1730201389995045 } } }, "_update_policy": { "total": 314.600216253, "count": 97, "self": 261.2806386340093, "children": { "TorchPPOOptimizer.update": { "total": 53.31957761899071, "count": 2910, "self": 53.31957761899071 } } } } } } }, "trainer_threads": { "total": 8.279998837679159e-07, "count": 1, "self": 8.279998837679159e-07 }, "TrainerController._save_models": { "total": 0.11440417099993283, "count": 1, "self": 0.002025120999860519, "children": { "RLTrainer._checkpoint": { "total": 0.11237905000007231, "count": 1, "self": 0.11237905000007231 } } } } } } }