ppo-Huggy / run_logs /timers.json
saranyabalakumar's picture
Huggy upload
2620c44 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4002020359039307,
"min": 1.400199294090271,
"max": 1.4262852668762207,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69671.25,
"min": 69190.7109375,
"max": 77266.90625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.91627172195892,
"min": 72.41409691629956,
"max": 421.109243697479,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49321.0,
"min": 49264.0,
"max": 50112.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999919.0,
"min": 49523.0,
"max": 1999919.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999919.0,
"min": 49523.0,
"max": 1999919.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.517169952392578,
"min": 0.10747287422418594,
"max": 2.53021240234375,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1593.36865234375,
"min": 12.681798934936523,
"max": 1676.590576171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8779199943534945,
"min": 1.7919951422234712,
"max": 4.145166344101689,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2454.723356425762,
"min": 211.4554267823696,
"max": 2666.4695021510124,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8779199943534945,
"min": 1.7919951422234712,
"max": 4.145166344101689,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2454.723356425762,
"min": 211.4554267823696,
"max": 2666.4695021510124,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01641371874914815,
"min": 0.013283269280024494,
"max": 0.022022887148583928,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04924115624744445,
"min": 0.026566538560048987,
"max": 0.05490340689818065,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06218356945448452,
"min": 0.021044966081778207,
"max": 0.06592066970964272,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18655070836345355,
"min": 0.042089932163556415,
"max": 0.18655070836345355,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.69589876806666e-06,
"min": 3.69589876806666e-06,
"max": 0.00029524350158550007,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.108769630419998e-05,
"min": 1.108769630419998e-05,
"max": 0.0008437209187596999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123193333333332,
"min": 0.10123193333333332,
"max": 0.19841450000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30369579999999996,
"min": 0.20763535,
"max": 0.5812403000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.147347333333323e-05,
"min": 7.147347333333323e-05,
"max": 0.0049208835499999996,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002144204199999997,
"min": 0.0002144204199999997,
"max": 0.01406389097,
"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": "1755682176",
"python_version": "3.10.12 (main, May 27 2025, 17:12:29) [GCC 11.4.0]",
"command_line_arguments": "/home/test/Saranya/reinforcement_learning/rl/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=/home/test/Saranya/reinforcement_learning/bonus-unit1/ml-agents/trained-envs-executables/linux/Huggy/Huggy.x86_64 --run-id=HuggyRun1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1755683774"
},
"total": 1597.315308113999,
"count": 1,
"self": 0.26969295099934243,
"children": {
"run_training.setup": {
"total": 0.010897793999902206,
"count": 1,
"self": 0.010897793999902206
},
"TrainerController.start_learning": {
"total": 1597.0347173689997,
"count": 1,
"self": 3.7058654495831433,
"children": {
"TrainerController._reset_env": {
"total": 0.9447633399995539,
"count": 1,
"self": 0.9447633399995539
},
"TrainerController.advance": {
"total": 1592.300064554419,
"count": 233510,
"self": 3.445970660448438,
"children": {
"env_step": {
"total": 1090.9431689650728,
"count": 233510,
"self": 925.2412550214676,
"children": {
"SubprocessEnvManager._take_step": {
"total": 163.25288140137582,
"count": 233510,
"self": 12.717441468336801,
"children": {
"TorchPolicy.evaluate": {
"total": 150.53543993303902,
"count": 222923,
"self": 150.53543993303902
}
}
},
"workers": {
"total": 2.449032542229361,
"count": 233510,
"self": 0.0,
"children": {
"worker_root": {
"total": 1592.2623774715112,
"count": 233510,
"is_parallel": true,
"self": 873.141011736172,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0005224480000833864,
"count": 1,
"is_parallel": true,
"self": 0.00017723800010571722,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003452099999776692,
"count": 2,
"is_parallel": true,
"self": 0.0003452099999776692
}
}
},
"UnityEnvironment.step": {
"total": 0.011869387999468017,
"count": 1,
"is_parallel": true,
"self": 0.000147858999298478,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00012180999965494266,
"count": 1,
"is_parallel": true,
"self": 0.00012180999965494266
},
"communicator.exchange": {
"total": 0.01130956100041658,
"count": 1,
"is_parallel": true,
"self": 0.01130956100041658
},
"steps_from_proto": {
"total": 0.0002901580000980175,
"count": 1,
"is_parallel": true,
"self": 0.00010038799973699497,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00018977000036102254,
"count": 2,
"is_parallel": true,
"self": 0.00018977000036102254
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 719.1213657353392,
"count": 233509,
"is_parallel": true,
"self": 22.964632431349855,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 39.85544491215478,
"count": 233509,
"is_parallel": true,
"self": 39.85544491215478
},
"communicator.exchange": {
"total": 605.4877558788858,
"count": 233509,
"is_parallel": true,
"self": 605.4877558788858
},
"steps_from_proto": {
"total": 50.81353251294877,
"count": 233509,
"is_parallel": true,
"self": 17.252585143989563,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.560947368959205,
"count": 467018,
"is_parallel": true,
"self": 33.560947368959205
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 497.91092492889766,
"count": 233510,
"self": 5.014387430117495,
"children": {
"process_trajectory": {
"total": 112.81181160977849,
"count": 233510,
"self": 112.20099415277946,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6108174569990297,
"count": 10,
"self": 0.6108174569990297
}
}
},
"_update_policy": {
"total": 380.0847258890017,
"count": 97,
"self": 157.67922929095585,
"children": {
"TorchPPOOptimizer.update": {
"total": 222.40549659804583,
"count": 2910,
"self": 222.40549659804583
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.1299983927747235e-06,
"count": 1,
"self": 2.1299983927747235e-06
},
"TrainerController._save_models": {
"total": 0.08402189499975066,
"count": 1,
"self": 0.0030357720006577438,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08098612299909291,
"count": 1,
"self": 0.08098612299909291
}
}
}
}
}
}
}