{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4045495986938477, "min": 1.4045495986938477, "max": 1.4255670309066772, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70238.71875, "min": 68949.2890625, "max": 76194.90625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.73344370860927, "min": 76.99375975039001, "max": 388.3333333333333, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49367.0, "min": 48962.0, "max": 50095.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999950.0, "min": 49595.0, "max": 1999950.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999950.0, "min": 49595.0, "max": 1999950.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4545838832855225, "min": 0.09020504355430603, "max": 2.4736902713775635, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1482.568603515625, "min": 11.546245574951172, "max": 1555.337890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8302265331642515, "min": 1.8511196298059076, "max": 3.9756024449239136, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2313.456826031208, "min": 236.94331261515617, "max": 2454.1937896609306, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8302265331642515, "min": 1.8511196298059076, "max": 3.9756024449239136, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2313.456826031208, "min": 236.94331261515617, "max": 2454.1937896609306, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019451615366900418, "min": 0.012722452919600377, "max": 0.019451615366900418, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.058354846100701255, "min": 0.025444905839200754, "max": 0.058354846100701255, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05426914191080465, "min": 0.021496590351065, "max": 0.06047966200858354, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16280742573241394, "min": 0.04299318070213, "max": 0.17785625606775285, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.777898740733342e-06, "min": 3.777898740733342e-06, "max": 0.00029535592654802496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1333696222200026e-05, "min": 1.1333696222200026e-05, "max": 0.0008441682186105997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10125926666666667, "min": 0.10125926666666667, "max": 0.19845197500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037778, "min": 0.20766135000000002, "max": 0.5813894, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.28374066666668e-05, "min": 7.28374066666668e-05, "max": 0.004922753552499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021851222000000042, "min": 0.00021851222000000042, "max": 0.014071331060000001, "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": "1685929897", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1685932628" }, "total": 2730.483975555, "count": 1, "self": 0.4880110440003591, "children": { "run_training.setup": { "total": 0.05040285399991262, "count": 1, "self": 0.05040285399991262 }, "TrainerController.start_learning": { "total": 2729.945561657, "count": 1, "self": 5.4296335121016455, "children": { "TrainerController._reset_env": { "total": 4.088466960000005, "count": 1, "self": 4.088466960000005 }, "TrainerController.advance": { "total": 2720.2938815418984, "count": 232768, "self": 5.524517759050013, "children": { "env_step": { "total": 2119.9015966570064, "count": 232768, "self": 1796.1107521219237, "children": { "SubprocessEnvManager._take_step": { "total": 320.40079264210976, "count": 232768, "self": 19.633270877083078, "children": { "TorchPolicy.evaluate": { "total": 300.7675217650267, "count": 222924, "self": 300.7675217650267 } } }, "workers": { "total": 3.390051892972906, "count": 232768, "self": 0.0, "children": { "worker_root": { "total": 2721.1281189709293, "count": 232768, "is_parallel": true, "self": 1254.720046063816, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010623829998621659, "count": 1, "is_parallel": true, "self": 0.0002865339997697447, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007758490000924212, "count": 2, "is_parallel": true, "self": 0.0007758490000924212 } } }, "UnityEnvironment.step": { "total": 0.03195236200008367, "count": 1, "is_parallel": true, "self": 0.00043332699988241075, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000271199000053457, "count": 1, "is_parallel": true, "self": 0.000271199000053457 }, "communicator.exchange": { "total": 0.030435563000082766, "count": 1, "is_parallel": true, "self": 0.030435563000082766 }, "steps_from_proto": { "total": 0.0008122730000650336, "count": 1, "is_parallel": true, "self": 0.00023950100012370967, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005727719999413239, "count": 2, "is_parallel": true, "self": 0.0005727719999413239 } } } } } } }, "UnityEnvironment.step": { "total": 1466.4080729071134, "count": 232767, "is_parallel": true, "self": 44.610062188030724, "children": { "UnityEnvironment._generate_step_input": { "total": 86.21369784208969, "count": 232767, "is_parallel": true, "self": 86.21369784208969 }, "communicator.exchange": { "total": 1227.4843375949404, "count": 232767, "is_parallel": true, "self": 1227.4843375949404 }, "steps_from_proto": { "total": 108.09997528205258, "count": 232767, "is_parallel": true, "self": 37.85004828014371, "children": { "_process_rank_one_or_two_observation": { "total": 70.24992700190887, "count": 465534, "is_parallel": true, "self": 70.24992700190887 } } } } } } } } } } }, "trainer_advance": { "total": 594.867767125842, "count": 232768, "self": 7.960195970896393, "children": { "process_trajectory": { "total": 150.31669705694662, "count": 232768, "self": 148.9564371869469, "children": { "RLTrainer._checkpoint": { "total": 1.3602598699997088, "count": 10, "self": 1.3602598699997088 } } }, "_update_policy": { "total": 436.59087409799895, "count": 97, "self": 370.8705824409906, "children": { "TorchPPOOptimizer.update": { "total": 65.72029165700837, "count": 2910, "self": 65.72029165700837 } } } } } } }, "trainer_threads": { "total": 1.0620001376082655e-06, "count": 1, "self": 1.0620001376082655e-06 }, "TrainerController._save_models": { "total": 0.13357858099971054, "count": 1, "self": 0.002217715999449865, "children": { "RLTrainer._checkpoint": { "total": 0.13136086500026067, "count": 1, "self": 0.13136086500026067 } } } } } } }