{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405854344367981, "min": 1.405854344367981, "max": 1.4299639463424683, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71283.84375, "min": 66524.75, "max": 79295.3359375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 94.35809523809523, "min": 83.56587837837837, "max": 394.79527559055117, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49538.0, "min": 48883.0, "max": 50202.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999963.0, "min": 49703.0, "max": 1999963.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999963.0, "min": 49703.0, "max": 1999963.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3849222660064697, "min": 0.0780317410826683, "max": 2.4722304344177246, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1252.084228515625, "min": 9.831999778747559, "max": 1461.088134765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7214353832744416, "min": 1.7672370809411246, "max": 3.9556405436691393, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1953.7535762190819, "min": 222.6718721985817, "max": 2243.0415620207787, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7214353832744416, "min": 1.7672370809411246, "max": 3.9556405436691393, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1953.7535762190819, "min": 222.6718721985817, "max": 2243.0415620207787, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01681895739149897, "min": 0.013829042985586662, "max": 0.021993728312211008, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05045687217449692, "min": 0.027658085971173325, "max": 0.06598118493663302, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05071070376369688, "min": 0.02157631960387031, "max": 0.06358005950848261, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15213211129109064, "min": 0.04315263920774062, "max": 0.18544680600365002, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3507988831000067e-06, "min": 3.3507988831000067e-06, "max": 0.000295332676555775, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.005239664930002e-05, "min": 1.005239664930002e-05, "max": 0.0008437206187597999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111690000000001, "min": 0.10111690000000001, "max": 0.19844422500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30335070000000003, "min": 0.20737965000000003, "max": 0.5812401999999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.573331000000012e-05, "min": 6.573331000000012e-05, "max": 0.004922366827499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019719993000000036, "min": 0.00019719993000000036, "max": 0.01406388598, "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": "1719212339", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719214762" }, "total": 2423.035788583, "count": 1, "self": 0.4849382490001517, "children": { "run_training.setup": { "total": 0.07729734999998072, "count": 1, "self": 0.07729734999998072 }, "TrainerController.start_learning": { "total": 2422.473552984, "count": 1, "self": 4.607422178921297, "children": { "TrainerController._reset_env": { "total": 3.46483602100011, "count": 1, "self": 3.46483602100011 }, "TrainerController.advance": { "total": 2414.275011804078, "count": 232332, "self": 4.749693419002597, "children": { "env_step": { "total": 1912.2568005741498, "count": 232332, "self": 1578.613036452318, "children": { "SubprocessEnvManager._take_step": { "total": 330.6855132398787, "count": 232332, "self": 19.054467131909405, "children": { "TorchPolicy.evaluate": { "total": 311.63104610796927, "count": 223048, "self": 311.63104610796927 } } }, "workers": { "total": 2.958250881953063, "count": 232332, "self": 0.0, "children": { "worker_root": { "total": 2415.081887378035, "count": 232332, "is_parallel": true, "self": 1148.8393417489876, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010930739999821526, "count": 1, "is_parallel": true, "self": 0.0002698130001590471, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008232609998231055, "count": 2, "is_parallel": true, "self": 0.0008232609998231055 } } }, "UnityEnvironment.step": { "total": 0.030596848999948634, "count": 1, "is_parallel": true, "self": 0.00038131399992380466, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019708699983311817, "count": 1, "is_parallel": true, "self": 0.00019708699983311817 }, "communicator.exchange": { "total": 0.029185209000161194, "count": 1, "is_parallel": true, "self": 0.029185209000161194 }, "steps_from_proto": { "total": 0.0008332390000305168, "count": 1, "is_parallel": true, "self": 0.00024367400010305573, "children": { "_process_rank_one_or_two_observation": { "total": 0.000589564999927461, "count": 2, "is_parallel": true, "self": 0.000589564999927461 } } } } } } }, "UnityEnvironment.step": { "total": 1266.2425456290473, "count": 232331, "is_parallel": true, "self": 39.85811857989347, "children": { "UnityEnvironment._generate_step_input": { "total": 80.00870744109261, "count": 232331, "is_parallel": true, "self": 80.00870744109261 }, "communicator.exchange": { "total": 1054.6839809981038, "count": 232331, "is_parallel": true, "self": 1054.6839809981038 }, "steps_from_proto": { "total": 91.69173860995738, "count": 232331, "is_parallel": true, "self": 32.165636502827056, "children": { "_process_rank_one_or_two_observation": { "total": 59.52610210713033, "count": 464662, "is_parallel": true, "self": 59.52610210713033 } } } } } } } } } } }, "trainer_advance": { "total": 497.2685178109259, "count": 232332, "self": 7.351680750984542, "children": { "process_trajectory": { "total": 153.28513063294417, "count": 232332, "self": 152.05464399694438, "children": { "RLTrainer._checkpoint": { "total": 1.230486635999796, "count": 10, "self": 1.230486635999796 } } }, "_update_policy": { "total": 336.6317064269972, "count": 97, "self": 271.0931422049946, "children": { "TorchPPOOptimizer.update": { "total": 65.5385642220026, "count": 2910, "self": 65.5385642220026 } } } } } } }, "trainer_threads": { "total": 1.0410003596916795e-06, "count": 1, "self": 1.0410003596916795e-06 }, "TrainerController._save_models": { "total": 0.12628193900036422, "count": 1, "self": 0.0026793010006258555, "children": { "RLTrainer._checkpoint": { "total": 0.12360263799973836, "count": 1, "self": 0.12360263799973836 } } } } } } }