{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4085955619812012, "min": 1.4085955619812012, "max": 1.42913818359375, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70949.546875, "min": 68507.6953125, "max": 76356.0859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.28776978417267, "min": 80.57096247960848, "max": 400.072, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49088.0, "min": 49071.0, "max": 50009.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999954.0, "min": 49894.0, "max": 1999954.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999954.0, "min": 49894.0, "max": 1999954.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.472074270248413, "min": 0.15924637019634247, "max": 2.477937698364258, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1374.4732666015625, "min": 19.746549606323242, "max": 1491.5274658203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.850363896261874, "min": 1.826816688141515, "max": 3.965327724922134, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2140.802326321602, "min": 226.52526932954788, "max": 2316.9926323890686, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.850363896261874, "min": 1.826816688141515, "max": 3.965327724922134, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2140.802326321602, "min": 226.52526932954788, "max": 2316.9926323890686, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01668566000039896, "min": 0.014109828296932391, "max": 0.021327105734477905, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050056980001196884, "min": 0.028219656593864783, "max": 0.05703028967691353, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05502370351718532, "min": 0.02096851859241724, "max": 0.06496741610268753, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16507111055155596, "min": 0.04193703718483448, "max": 0.18499911949038506, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.35009888333333e-06, "min": 3.35009888333333e-06, "max": 0.00029532225155924993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.005029664999999e-05, "min": 1.005029664999999e-05, "max": 0.0008439214686928498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111666666666667, "min": 0.10111666666666667, "max": 0.19844075000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30335, "min": 0.20737894999999998, "max": 0.58130715, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.572166666666663e-05, "min": 6.572166666666663e-05, "max": 0.004922193425000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019716499999999988, "min": 0.00019716499999999988, "max": 0.014067226784999998, "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": "1670875646", "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": "1670877805" }, "total": 2158.486982511, "count": 1, "self": 0.3905881360001331, "children": { "run_training.setup": { "total": 0.10623093899999958, "count": 1, "self": 0.10623093899999958 }, "TrainerController.start_learning": { "total": 2157.990163436, "count": 1, "self": 3.6982750880447384, "children": { "TrainerController._reset_env": { "total": 10.312296010000011, "count": 1, "self": 10.312296010000011 }, "TrainerController.advance": { "total": 2143.868187329955, "count": 232782, "self": 3.9483768620470983, "children": { "env_step": { "total": 1680.535987599947, "count": 232782, "self": 1408.6570077899983, "children": { "SubprocessEnvManager._take_step": { "total": 269.3902214990408, "count": 232782, "self": 13.86986571199634, "children": { "TorchPolicy.evaluate": { "total": 255.52035578704448, "count": 223014, "self": 64.2745947640891, "children": { "TorchPolicy.sample_actions": { "total": 191.24576102295538, "count": 223014, "self": 191.24576102295538 } } } } }, "workers": { "total": 2.4887583109078264, "count": 232782, "self": 0.0, "children": { "worker_root": { "total": 2150.5369853940574, "count": 232782, "is_parallel": true, "self": 991.8166286050841, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001952205000009144, "count": 1, "is_parallel": true, "self": 0.00032428899999104033, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016279160000181037, "count": 2, "is_parallel": true, "self": 0.0016279160000181037 } } }, "UnityEnvironment.step": { "total": 0.03004080900001327, "count": 1, "is_parallel": true, "self": 0.00026795799999490555, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018040499998051018, "count": 1, "is_parallel": true, "self": 0.00018040499998051018 }, "communicator.exchange": { "total": 0.028883955000026162, "count": 1, "is_parallel": true, "self": 0.028883955000026162 }, "steps_from_proto": { "total": 0.0007084910000116906, "count": 1, "is_parallel": true, "self": 0.0002447319999987485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004637590000129421, "count": 2, "is_parallel": true, "self": 0.0004637590000129421 } } } } } } }, "UnityEnvironment.step": { "total": 1158.7203567889733, "count": 232781, "is_parallel": true, "self": 34.40572150272669, "children": { "UnityEnvironment._generate_step_input": { "total": 75.22156169906322, "count": 232781, "is_parallel": true, "self": 75.22156169906322 }, "communicator.exchange": { "total": 958.0187422020999, "count": 232781, "is_parallel": true, "self": 958.0187422020999 }, "steps_from_proto": { "total": 91.0743313850835, "count": 232781, "is_parallel": true, "self": 37.520075818196744, "children": { "_process_rank_one_or_two_observation": { "total": 53.55425556688675, "count": 465562, "is_parallel": true, "self": 53.55425556688675 } } } } } } } } } } }, "trainer_advance": { "total": 459.383822867961, "count": 232782, "self": 5.842758490982931, "children": { "process_trajectory": { "total": 145.01140295497714, "count": 232782, "self": 144.54100463297755, "children": { "RLTrainer._checkpoint": { "total": 0.4703983219995962, "count": 4, "self": 0.4703983219995962 } } }, "_update_policy": { "total": 308.5296614220009, "count": 97, "self": 255.9774852470012, "children": { "TorchPPOOptimizer.update": { "total": 52.552176174999715, "count": 2910, "self": 52.552176174999715 } } } } } } }, "trainer_threads": { "total": 9.600003068044316e-07, "count": 1, "self": 9.600003068044316e-07 }, "TrainerController._save_models": { "total": 0.11140404799971293, "count": 1, "self": 0.001935944999786443, "children": { "RLTrainer._checkpoint": { "total": 0.10946810299992649, "count": 1, "self": 0.10946810299992649 } } } } } } }