{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4124964475631714, "min": 1.4124964475631714, "max": 1.4332290887832642, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69435.5, "min": 69435.5, "max": 77730.9375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 106.09533898305085, "min": 86.29668411867365, "max": 393.15748031496065, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50077.0, "min": 48788.0, "max": 50204.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999815.0, "min": 49855.0, "max": 1999815.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999815.0, "min": 49855.0, "max": 1999815.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.2940144538879395, "min": 0.19657105207443237, "max": 2.3658432960510254, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1082.7747802734375, "min": 24.76795196533203, "max": 1332.135009765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5333845746719232, "min": 1.940038989105868, "max": 3.85069164450352, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1667.7575192451477, "min": 244.44491262733936, "max": 2148.195804655552, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5333845746719232, "min": 1.940038989105868, "max": 3.85069164450352, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1667.7575192451477, "min": 244.44491262733936, "max": 2148.195804655552, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01802390245356946, "min": 0.013168269910359716, "max": 0.019912561735125362, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03604780490713892, "min": 0.026336539820719432, "max": 0.05973768520537608, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04292387031018734, "min": 0.019601298651347555, "max": 0.06508148976912101, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08584774062037467, "min": 0.03920259730269511, "max": 0.18011412198344867, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.549973483374997e-06, "min": 4.549973483374997e-06, "max": 0.000295296826567725, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.099946966749994e-06, "min": 9.099946966749994e-06, "max": 0.0008436670687776498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10151662499999999, "min": 0.10151662499999999, "max": 0.198432275, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20303324999999997, "min": 0.20303324999999997, "max": 0.5812223500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.567958749999997e-05, "min": 8.567958749999997e-05, "max": 0.004921770522499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017135917499999995, "min": 0.00017135917499999995, "max": 0.014062995264999998, "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": "1690199677", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690202429" }, "total": 2752.5162251829997, "count": 1, "self": 0.4384780559998944, "children": { "run_training.setup": { "total": 0.03393115599999419, "count": 1, "self": 0.03393115599999419 }, "TrainerController.start_learning": { "total": 2752.0438159709997, "count": 1, "self": 5.076957923030022, "children": { "TrainerController._reset_env": { "total": 6.087382416999958, "count": 1, "self": 6.087382416999958 }, "TrainerController.advance": { "total": 2740.75824771097, "count": 230997, "self": 5.233432196945614, "children": { "env_step": { "total": 2131.963825032968, "count": 230997, "self": 1802.0278395980672, "children": { "SubprocessEnvManager._take_step": { "total": 326.55744916093886, "count": 230997, "self": 19.098405744848606, "children": { "TorchPolicy.evaluate": { "total": 307.45904341609025, "count": 222964, "self": 307.45904341609025 } } }, "workers": { "total": 3.3785362739621405, "count": 230997, "self": 0.0, "children": { "worker_root": { "total": 2743.2954128190395, "count": 230997, "is_parallel": true, "self": 1276.164030156105, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009382459999187631, "count": 1, "is_parallel": true, "self": 0.00028371500002322136, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006545309998955418, "count": 2, "is_parallel": true, "self": 0.0006545309998955418 } } }, "UnityEnvironment.step": { "total": 0.059313765999945645, "count": 1, "is_parallel": true, "self": 0.00039979400003176124, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002460279999922932, "count": 1, "is_parallel": true, "self": 0.0002460279999922932 }, "communicator.exchange": { "total": 0.057777864999934536, "count": 1, "is_parallel": true, "self": 0.057777864999934536 }, "steps_from_proto": { "total": 0.000890078999987054, "count": 1, "is_parallel": true, "self": 0.0002545789999430781, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006355000000439759, "count": 2, "is_parallel": true, "self": 0.0006355000000439759 } } } } } } }, "UnityEnvironment.step": { "total": 1467.1313826629346, "count": 230996, "is_parallel": true, "self": 44.57373920186251, "children": { "UnityEnvironment._generate_step_input": { "total": 92.88240305603233, "count": 230996, "is_parallel": true, "self": 92.88240305603233 }, "communicator.exchange": { "total": 1221.056559160955, "count": 230996, "is_parallel": true, "self": 1221.056559160955 }, "steps_from_proto": { "total": 108.61868124408466, "count": 230996, "is_parallel": true, "self": 41.70409265394426, "children": { "_process_rank_one_or_two_observation": { "total": 66.9145885901404, "count": 461992, "is_parallel": true, "self": 66.9145885901404 } } } } } } } } } } }, "trainer_advance": { "total": 603.5609904810565, "count": 230997, "self": 7.501481693118194, "children": { "process_trajectory": { "total": 151.13674864193536, "count": 230997, "self": 149.73765242593527, "children": { "RLTrainer._checkpoint": { "total": 1.399096216000089, "count": 10, "self": 1.399096216000089 } } }, "_update_policy": { "total": 444.92276014600293, "count": 96, "self": 382.48500990699426, "children": { "TorchPPOOptimizer.update": { "total": 62.437750239008665, "count": 2880, "self": 62.437750239008665 } } } } } } }, "trainer_threads": { "total": 9.51999936660286e-07, "count": 1, "self": 9.51999936660286e-07 }, "TrainerController._save_models": { "total": 0.12122696799997357, "count": 1, "self": 0.0018540740002208622, "children": { "RLTrainer._checkpoint": { "total": 0.1193728939997527, "count": 1, "self": 0.1193728939997527 } } } } } } }