Falguni's picture
Push to huggingface hub
0ec7e20
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8793655037879944,
"min": 0.8793655037879944,
"max": 2.8640050888061523,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8425.201171875,
"min": 8425.201171875,
"max": 29424.787109375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 11.965179443359375,
"min": 0.3150251805782318,
"max": 11.965179443359375,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2333.2099609375,
"min": 61.11488342285156,
"max": 2407.9140625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06771288319806426,
"min": 0.06176096369574011,
"max": 0.07763966255824212,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27085153279225704,
"min": 0.24704385478296045,
"max": 0.3881983127912106,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.196006843235855,
"min": 0.12648093580797898,
"max": 0.2697693225653732,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.78402737294342,
"min": 0.5059237432319159,
"max": 1.3265637322968127,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 23.795454545454547,
"min": 3.409090909090909,
"max": 23.795454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1047.0,
"min": 150.0,
"max": 1294.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.795454545454547,
"min": 3.409090909090909,
"max": 23.795454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1047.0,
"min": 150.0,
"max": 1294.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1684564626",
"python_version": "3.8.16 (default, Mar 2 2023, 03:21:46) \n[GCC 11.2.0]",
"command_line_arguments": "/home/falguni/anaconda3/envs/huggingface_rl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1684565032"
},
"total": 406.09373670399873,
"count": 1,
"self": 0.32258461399760563,
"children": {
"run_training.setup": {
"total": 0.01617845200053125,
"count": 1,
"self": 0.01617845200053125
},
"TrainerController.start_learning": {
"total": 405.7549736380006,
"count": 1,
"self": 0.497496775820764,
"children": {
"TrainerController._reset_env": {
"total": 3.027580444000705,
"count": 1,
"self": 3.027580444000705
},
"TrainerController.advance": {
"total": 402.11217013817804,
"count": 18206,
"self": 0.25929095605170005,
"children": {
"env_step": {
"total": 401.85287918212634,
"count": 18206,
"self": 285.36379747224964,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.20931018594092,
"count": 18206,
"self": 1.7043658951079124,
"children": {
"TorchPolicy.evaluate": {
"total": 114.50494429083301,
"count": 18206,
"self": 114.50494429083301
}
}
},
"workers": {
"total": 0.27977152393577853,
"count": 18206,
"self": 0.0,
"children": {
"worker_root": {
"total": 404.9336173849715,
"count": 18206,
"is_parallel": true,
"self": 190.8563032191687,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0026589110002532834,
"count": 1,
"is_parallel": true,
"self": 0.0012337730040599126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014251379961933708,
"count": 10,
"is_parallel": true,
"self": 0.0014251379961933708
}
}
},
"UnityEnvironment.step": {
"total": 0.031652666000809404,
"count": 1,
"is_parallel": true,
"self": 0.0009723540006234543,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004190340005152393,
"count": 1,
"is_parallel": true,
"self": 0.0004190340005152393
},
"communicator.exchange": {
"total": 0.027957158999925014,
"count": 1,
"is_parallel": true,
"self": 0.027957158999925014
},
"steps_from_proto": {
"total": 0.0023041189997456968,
"count": 1,
"is_parallel": true,
"self": 0.000262614003077033,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002041504996668664,
"count": 10,
"is_parallel": true,
"self": 0.002041504996668664
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.07731416580282,
"count": 18205,
"is_parallel": true,
"self": 11.699452692590057,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.152150028085089,
"count": 18205,
"is_parallel": true,
"self": 5.152150028085089
},
"communicator.exchange": {
"total": 165.75950654200278,
"count": 18205,
"is_parallel": true,
"self": 165.75950654200278
},
"steps_from_proto": {
"total": 31.46620490312489,
"count": 18205,
"is_parallel": true,
"self": 5.451516239621924,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.014688663502966,
"count": 182050,
"is_parallel": true,
"self": 26.014688663502966
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011736400119843893,
"count": 1,
"self": 0.00011736400119843893,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 400.4618567354846,
"count": 263448,
"is_parallel": true,
"self": 5.053672043866754,
"children": {
"process_trajectory": {
"total": 227.74555616262842,
"count": 263448,
"is_parallel": true,
"self": 226.85594232862968,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8896138339987374,
"count": 4,
"is_parallel": true,
"self": 0.8896138339987374
}
}
},
"_update_policy": {
"total": 167.66262852898944,
"count": 90,
"is_parallel": true,
"self": 43.63644349592323,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.02618503306621,
"count": 4587,
"is_parallel": true,
"self": 124.02618503306621
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11760891599988099,
"count": 1,
"self": 0.0009283670005970635,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11668054899928393,
"count": 1,
"self": 0.11668054899928393
}
}
}
}
}
}
}