{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405936598777771, "min": 1.405936598777771, "max": 1.4279758930206299, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71030.7265625, "min": 68971.984375, "max": 78260.578125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 98.29821073558648, "min": 84.54358974358975, "max": 380.75, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49444.0, "min": 48894.0, "max": 50259.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999851.0, "min": 49804.0, "max": 1999851.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999851.0, "min": 49804.0, "max": 1999851.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4140377044677734, "min": 0.09922930598258972, "max": 2.450228214263916, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1214.260986328125, "min": 12.999038696289062, "max": 1388.60498046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7791157683605703, "min": 1.801224200780155, "max": 3.9519849332896144, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1900.8952314853668, "min": 235.96037030220032, "max": 2185.357919573784, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7791157683605703, "min": 1.801224200780155, "max": 3.9519849332896144, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1900.8952314853668, "min": 235.96037030220032, "max": 2185.357919573784, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016025023964498866, "min": 0.01403059961157851, "max": 0.020063904911431663, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04807507189349659, "min": 0.029119760141475125, "max": 0.06019171473429499, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.051660810328192176, "min": 0.021314411672453085, "max": 0.060358540154993534, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15498243098457654, "min": 0.04262882334490617, "max": 0.17280518623689808, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4222988592666634e-06, "min": 3.4222988592666634e-06, "max": 0.0002953296015568, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.026689657779999e-05, "min": 1.026689657779999e-05, "max": 0.0008439930186689999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114073333333333, "min": 0.10114073333333333, "max": 0.1984432, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034222, "min": 0.20741845000000003, "max": 0.5813309999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.692259333333328e-05, "min": 6.692259333333328e-05, "max": 0.004922315679999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020076777999999984, "min": 0.00020076777999999984, "max": 0.0140684169, "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": "1672235594", "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": "1672237797" }, "total": 2202.7331866910004, "count": 1, "self": 0.3890647180000997, "children": { "run_training.setup": { "total": 0.3105755469999849, "count": 1, "self": 0.3105755469999849 }, "TrainerController.start_learning": { "total": 2202.033546426, "count": 1, "self": 3.8225638899771184, "children": { "TrainerController._reset_env": { "total": 8.459978647000014, "count": 1, "self": 8.459978647000014 }, "TrainerController.advance": { "total": 2189.6274729300226, "count": 232080, "self": 3.945035824858678, "children": { "env_step": { "total": 1720.2220150721014, "count": 232080, "self": 1445.7185618431317, "children": { "SubprocessEnvManager._take_step": { "total": 272.01081711299616, "count": 232080, "self": 13.923824901010278, "children": { "TorchPolicy.evaluate": { "total": 258.0869922119859, "count": 222984, "self": 65.1004741589507, "children": { "TorchPolicy.sample_actions": { "total": 192.98651805303518, "count": 222984, "self": 192.98651805303518 } } } } }, "workers": { "total": 2.4926361159734256, "count": 232080, "self": 0.0, "children": { "worker_root": { "total": 2194.558658069002, "count": 232080, "is_parallel": true, "self": 1002.3634242570349, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002217052999981206, "count": 1, "is_parallel": true, "self": 0.0003292279999982384, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018878249999829677, "count": 2, "is_parallel": true, "self": 0.0018878249999829677 } } }, "UnityEnvironment.step": { "total": 0.030811835000008614, "count": 1, "is_parallel": true, "self": 0.00030102400000942, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001900440000213166, "count": 1, "is_parallel": true, "self": 0.0001900440000213166 }, "communicator.exchange": { "total": 0.02948705199997903, "count": 1, "is_parallel": true, "self": 0.02948705199997903 }, "steps_from_proto": { "total": 0.0008337149999988469, "count": 1, "is_parallel": true, "self": 0.00027824199992210197, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005554730000767449, "count": 2, "is_parallel": true, "self": 0.0005554730000767449 } } } } } } }, "UnityEnvironment.step": { "total": 1192.195233811967, "count": 232079, "is_parallel": true, "self": 34.13120158597576, "children": { "UnityEnvironment._generate_step_input": { "total": 75.19968911098834, "count": 232079, "is_parallel": true, "self": 75.19968911098834 }, "communicator.exchange": { "total": 990.5227388709634, "count": 232079, "is_parallel": true, "self": 990.5227388709634 }, "steps_from_proto": { "total": 92.34160424403939, "count": 232079, "is_parallel": true, "self": 37.67274472504823, "children": { "_process_rank_one_or_two_observation": { "total": 54.668859518991155, "count": 464158, "is_parallel": true, "self": 54.668859518991155 } } } } } } } } } } }, "trainer_advance": { "total": 465.46042203306257, "count": 232080, "self": 5.830089984954043, "children": { "process_trajectory": { "total": 142.4577582701089, "count": 232080, "self": 141.28144319310883, "children": { "RLTrainer._checkpoint": { "total": 1.1763150770000834, "count": 10, "self": 1.1763150770000834 } } }, "_update_policy": { "total": 317.1725737779996, "count": 97, "self": 264.3151105120001, "children": { "TorchPPOOptimizer.update": { "total": 52.85746326599951, "count": 2910, "self": 52.85746326599951 } } } } } } }, "trainer_threads": { "total": 9.73000169324223e-07, "count": 1, "self": 9.73000169324223e-07 }, "TrainerController._save_models": { "total": 0.12352998600044884, "count": 1, "self": 0.001962277000075119, "children": { "RLTrainer._checkpoint": { "total": 0.12156770900037372, "count": 1, "self": 0.12156770900037372 } } } } } } }