{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4009262323379517, "min": 1.4009262323379517, "max": 1.427578330039978, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68886.34375, "min": 68202.59375, "max": 76983.4609375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.17857142857143, "min": 79.7373572593801, "max": 396.0, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49390.0, "min": 48879.0, "max": 50292.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999904.0, "min": 49925.0, "max": 1999904.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999904.0, "min": 49925.0, "max": 1999904.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.436591148376465, "min": 0.12015644460916519, "max": 2.4944279193878174, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1500.940185546875, "min": 15.1397123336792, "max": 1536.567626953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7045986868150824, "min": 1.7023673848736853, "max": 3.9520273820930987, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2282.0327910780907, "min": 214.49829049408436, "max": 2423.221585690975, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7045986868150824, "min": 1.7023673848736853, "max": 3.9520273820930987, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2282.0327910780907, "min": 214.49829049408436, "max": 2423.221585690975, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016279737923953996, "min": 0.013769613095306948, "max": 0.019777205047709384, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04883921377186198, "min": 0.028829436399488866, "max": 0.05677547647501342, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054274493952592213, "min": 0.021654841986795265, "max": 0.058442500771747695, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16282348185777665, "min": 0.04330968397359053, "max": 0.17532750231524308, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.810748729783326e-06, "min": 3.810748729783326e-06, "max": 0.0002953338015554, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1432246189349978e-05, "min": 1.1432246189349978e-05, "max": 0.0008438100187299999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127021666666665, "min": 0.10127021666666665, "max": 0.19844459999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30381064999999996, "min": 0.20766645, "max": 0.5812699999999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.338381166666656e-05, "min": 7.338381166666656e-05, "max": 0.004922385540000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022015143499999967, "min": 0.00022015143499999967, "max": 0.014065372999999999, "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": "1670865621", "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": "1670867768" }, "total": 2146.5872289830004, "count": 1, "self": 0.3891846289998284, "children": { "run_training.setup": { "total": 0.10626759600006608, "count": 1, "self": 0.10626759600006608 }, "TrainerController.start_learning": { "total": 2146.0917767580004, "count": 1, "self": 3.784405380997214, "children": { "TrainerController._reset_env": { "total": 9.850729608000051, "count": 1, "self": 9.850729608000051 }, "TrainerController.advance": { "total": 2132.3446635980026, "count": 232638, "self": 4.051167041028748, "children": { "env_step": { "total": 1672.1709022290472, "count": 232638, "self": 1407.7497174110922, "children": { "SubprocessEnvManager._take_step": { "total": 261.9530824339596, "count": 232638, "self": 13.96712073099377, "children": { "TorchPolicy.evaluate": { "total": 247.98596170296582, "count": 222894, "self": 62.64238851592131, "children": { "TorchPolicy.sample_actions": { "total": 185.3435731870445, "count": 222894, "self": 185.3435731870445 } } } } }, "workers": { "total": 2.4681023839953014, "count": 232638, "self": 0.0, "children": { "worker_root": { "total": 2138.56698010401, "count": 232638, "is_parallel": true, "self": 977.0989391269916, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001830715999972199, "count": 1, "is_parallel": true, "self": 0.0002993440000409464, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015313719999312525, "count": 2, "is_parallel": true, "self": 0.0015313719999312525 } } }, "UnityEnvironment.step": { "total": 0.02671823800005768, "count": 1, "is_parallel": true, "self": 0.0002705320000586653, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022764599998481572, "count": 1, "is_parallel": true, "self": 0.00022764599998481572 }, "communicator.exchange": { "total": 0.025542299999983697, "count": 1, "is_parallel": true, "self": 0.025542299999983697 }, "steps_from_proto": { "total": 0.0006777600000305029, "count": 1, "is_parallel": true, "self": 0.0002265470000111236, "children": { "_process_rank_one_or_two_observation": { "total": 0.00045121300001937925, "count": 2, "is_parallel": true, "self": 0.00045121300001937925 } } } } } } }, "UnityEnvironment.step": { "total": 1161.4680409770183, "count": 232637, "is_parallel": true, "self": 33.83570332513068, "children": { "UnityEnvironment._generate_step_input": { "total": 74.46047425795575, "count": 232637, "is_parallel": true, "self": 74.46047425795575 }, "communicator.exchange": { "total": 963.4713108729394, "count": 232637, "is_parallel": true, "self": 963.4713108729394 }, "steps_from_proto": { "total": 89.70055252099257, "count": 232637, "is_parallel": true, "self": 36.864444117923426, "children": { "_process_rank_one_or_two_observation": { "total": 52.83610840306915, "count": 465274, "is_parallel": true, "self": 52.83610840306915 } } } } } } } } } } }, "trainer_advance": { "total": 456.12259432792644, "count": 232638, "self": 5.60258689691932, "children": { "process_trajectory": { "total": 143.56875733800598, "count": 232638, "self": 143.10894722900616, "children": { "RLTrainer._checkpoint": { "total": 0.4598101089998181, "count": 4, "self": 0.4598101089998181 } } }, "_update_policy": { "total": 306.95125009300114, "count": 97, "self": 254.85160683200036, "children": { "TorchPPOOptimizer.update": { "total": 52.09964326100078, "count": 2910, "self": 52.09964326100078 } } } } } } }, "trainer_threads": { "total": 9.55000359681435e-07, "count": 1, "self": 9.55000359681435e-07 }, "TrainerController._save_models": { "total": 0.11197721600001387, "count": 1, "self": 0.0020785170004273823, "children": { "RLTrainer._checkpoint": { "total": 0.10989869899958649, "count": 1, "self": 0.10989869899958649 } } } } } } }