{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4018433094024658, "min": 1.4018433094024658, "max": 1.4277427196502686, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69115.078125, "min": 68636.7421875, "max": 75893.6796875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.17171717171718, "min": 78.35955056179775, "max": 403.03225806451616, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48810.0, "min": 48810.0, "max": 49978.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999944.0, "min": 49684.0, "max": 1999944.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999944.0, "min": 49684.0, "max": 1999944.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.453338623046875, "min": -0.04823176562786102, "max": 2.4573044776916504, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1457.283203125, "min": -5.932507038116455, "max": 1505.253662109375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.829572378083913, "min": 1.5369466848489715, "max": 3.9741147357718387, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2274.7659925818443, "min": 189.0444422364235, "max": 2389.2634751796722, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.829572378083913, "min": 1.5369466848489715, "max": 3.9741147357718387, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2274.7659925818443, "min": 189.0444422364235, "max": 2389.2634751796722, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015164625430608996, "min": 0.014341046778038921, "max": 0.021561302426319647, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04549387629182699, "min": 0.028682093556077842, "max": 0.06253359501133673, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05338211419681708, "min": 0.022740358517815668, "max": 0.06378283469627301, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16014634259045124, "min": 0.045480717035631335, "max": 0.1907971365998189, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6101487966499986e-06, "min": 3.6101487966499986e-06, "max": 0.0002953293015569, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0830446389949996e-05, "min": 1.0830446389949996e-05, "max": 0.0008439970686676499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120335000000001, "min": 0.10120335000000001, "max": 0.1984431, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30361005, "min": 0.20753405000000003, "max": 0.58133235, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.004716499999997e-05, "min": 7.004716499999997e-05, "max": 0.004922310690000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002101414949999999, "min": 0.0002101414949999999, "max": 0.014068484264999999, "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": "1679652681", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/home/ummagumma/personal/huggingface_rl/env/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": "1679654814" }, "total": 2132.8677174355835, "count": 1, "self": 0.42084123380482197, "children": { "run_training.setup": { "total": 0.018077922984957695, "count": 1, "self": 0.018077922984957695 }, "TrainerController.start_learning": { "total": 2132.4287982787937, "count": 1, "self": 2.822715474292636, "children": { "TrainerController._reset_env": { "total": 3.0702766459435225, "count": 1, "self": 3.0702766459435225 }, "TrainerController.advance": { "total": 2126.4159332159907, "count": 232420, "self": 3.013344781473279, "children": { "env_step": { "total": 1807.297152152285, "count": 232420, "self": 1621.012469097972, "children": { "SubprocessEnvManager._take_step": { "total": 184.37693233042955, "count": 232420, "self": 10.862324165180326, "children": { "TorchPolicy.evaluate": { "total": 173.51460816524923, "count": 222903, "self": 173.51460816524923 } } }, "workers": { "total": 1.9077507238835096, "count": 232420, "self": 0.0, "children": { "worker_root": { "total": 2124.0008942857385, "count": 232420, "is_parallel": true, "self": 751.9864830896258, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001384492963552475, "count": 1, "is_parallel": true, "self": 0.00041896291077136993, "children": { "_process_rank_one_or_two_observation": { "total": 0.000965530052781105, "count": 2, "is_parallel": true, "self": 0.000965530052781105 } } }, "UnityEnvironment.step": { "total": 0.032528094947338104, "count": 1, "is_parallel": true, "self": 0.0004730653017759323, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002926420420408249, "count": 1, "is_parallel": true, "self": 0.0002926420420408249 }, "communicator.exchange": { "total": 0.03077707439661026, "count": 1, "is_parallel": true, "self": 0.03077707439661026 }, "steps_from_proto": { "total": 0.000985313206911087, "count": 1, "is_parallel": true, "self": 0.0002942606806755066, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006910525262355804, "count": 2, "is_parallel": true, "self": 0.0006910525262355804 } } } } } } }, "UnityEnvironment.step": { "total": 1372.0144111961126, "count": 232419, "is_parallel": true, "self": 41.58648641221225, "children": { "UnityEnvironment._generate_step_input": { "total": 83.28991876915097, "count": 232419, "is_parallel": true, "self": 83.28991876915097 }, "communicator.exchange": { "total": 1152.861523438245, "count": 232419, "is_parallel": true, "self": 1152.861523438245 }, "steps_from_proto": { "total": 94.27648257650435, "count": 232419, "is_parallel": true, "self": 36.11769083701074, "children": { "_process_rank_one_or_two_observation": { "total": 58.15879173949361, "count": 464838, "is_parallel": true, "self": 58.15879173949361 } } } } } } } } } } }, "trainer_advance": { "total": 316.1054362822324, "count": 232420, "self": 3.970396926626563, "children": { "process_trajectory": { "total": 81.05346230231225, "count": 232420, "self": 79.86158644594252, "children": { "RLTrainer._checkpoint": { "total": 1.1918758563697338, "count": 10, "self": 1.1918758563697338 } } }, "_update_policy": { "total": 231.08157705329359, "count": 97, "self": 189.95173043571413, "children": { "TorchPPOOptimizer.update": { "total": 41.12984661757946, "count": 2910, "self": 41.12984661757946 } } } } } } }, "trainer_threads": { "total": 8.791685104370117e-07, "count": 1, "self": 8.791685104370117e-07 }, "TrainerController._save_models": { "total": 0.1198720633983612, "count": 1, "self": 0.001544758677482605, "children": { "RLTrainer._checkpoint": { "total": 0.1183273047208786, "count": 1, "self": 0.1183273047208786 } } } } } } }