ppo-Pyramids / run_logs /timers.json
Lpremier's picture
Add pyramids agent.
3aab382 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.9219416975975037,
"min": 0.9219416975975037,
"max": 1.3308157920837402,
"count": 3
},
"Pyramids.Policy.Entropy.sum": {
"value": 28056.529296875,
"min": 28056.529296875,
"max": 40371.62890625,
"count": 3
},
"Pyramids.Step.mean": {
"value": 89998.0,
"min": 29893.0,
"max": 89998.0,
"count": 3
},
"Pyramids.Step.sum": {
"value": 89998.0,
"min": 29893.0,
"max": 89998.0,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.05693092569708824,
"min": -0.057289861142635345,
"max": 0.010499139316380024,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -13.777283668518066,
"min": -13.86414623260498,
"max": 2.4882960319519043,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.19356770813465118,
"min": 0.19356770813465118,
"max": 0.652888834476471,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 46.8433837890625,
"min": 46.8433837890625,
"max": 154.73464965820312,
"count": 3
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.09366758631134031,
"min": 0.09366758631134031,
"max": 0.10365323002324789,
"count": 3
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.1240110357360837,
"min": 0.8292258401859831,
"max": 1.1240110357360837,
"count": 3
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0011701008608305148,
"min": 0.0011701008608305148,
"max": 0.013040119442371574,
"count": 3
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.014041210329966178,
"min": 0.014041210329966178,
"max": 0.1043209555389726,
"count": 3
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00010079474146799999,
"min": 0.00010079474146799999,
"max": 0.00033128851717787496,
"count": 3
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.001209536897616,
"min": 0.001209536897616,
"max": 0.0026503081374229997,
"count": 3
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.12519866666666665,
"min": 0.12519866666666665,
"max": 0.182822125,
"count": 3
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.502384,
"min": 1.462577,
"max": 1.5484120000000001,
"count": 3
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0025273467999999996,
"min": 0.0025273467999999996,
"max": 0.0082839302875,
"count": 3
},
"Pyramids.Policy.Beta.sum": {
"value": 0.030328161599999993,
"min": 0.030328161599999993,
"max": 0.0662714423,
"count": 3
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.10764492303133011,
"min": 0.10764492303133011,
"max": 0.7087070941925049,
"count": 3
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 1.2917391061782837,
"min": 1.2917391061782837,
"max": 5.669656753540039,
"count": 3
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 962.7272727272727,
"min": 959.2941176470588,
"max": 988.5151515151515,
"count": 3
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31770.0,
"min": 16308.0,
"max": 32621.0,
"count": 3
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.842418231521592,
"min": -0.8682242952512972,
"max": -0.842418231521592,
"count": 3
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -27.799801640212536,
"min": -28.65140174329281,
"max": -14.324000805616379,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.842418231521592,
"min": -0.8682242952512972,
"max": -0.842418231521592,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -27.799801640212536,
"min": -28.65140174329281,
"max": -14.324000805616379,
"count": 3
},
"Pyramids.Policy.RndReward.mean": {
"value": 1.2287372043638518,
"min": 1.2287372043638518,
"max": 15.582255615907556,
"count": 3
},
"Pyramids.Policy.RndReward.sum": {
"value": 40.54832774400711,
"min": 40.54832774400711,
"max": 264.89834547042847,
"count": 3
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1738882241",
"python_version": "3.11.2 (main, Nov 30 2024, 21:22:50) [GCC 12.2.0]",
"command_line_arguments": "/home/lucien/Workspace/deep-rl-hugging-face/.venv/bin/mlagents-learn ./Pyramids.yaml --env=./envs/Pyramids/Pyramids --run-id=Pyramids --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cpu",
"numpy_version": "1.23.5",
"end_time_seconds": "1738882570"
},
"total": 329.23776459897636,
"count": 1,
"self": 0.32012054495862685,
"children": {
"run_training.setup": {
"total": 0.020413690013810992,
"count": 1,
"self": 0.020413690013810992
},
"TrainerController.start_learning": {
"total": 328.8972303640039,
"count": 1,
"self": 0.09587996121263131,
"children": {
"TrainerController._reset_env": {
"total": 2.221178787993267,
"count": 1,
"self": 2.221178787993267
},
"TrainerController.advance": {
"total": 326.40558701378177,
"count": 6318,
"self": 0.07535588680184446,
"children": {
"env_step": {
"total": 281.7097327912343,
"count": 6318,
"self": 274.31891261739656,
"children": {
"SubprocessEnvManager._take_step": {
"total": 7.331330438988516,
"count": 6318,
"self": 0.3121476978994906,
"children": {
"TorchPolicy.evaluate": {
"total": 7.0191827410890255,
"count": 6310,
"self": 7.0191827410890255
}
}
},
"workers": {
"total": 0.059489734849194065,
"count": 6318,
"self": 0.0,
"children": {
"worker_root": {
"total": 328.5259574865049,
"count": 6318,
"is_parallel": true,
"self": 63.05742806071066,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002009084011660889,
"count": 1,
"is_parallel": true,
"self": 0.001066856988472864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009422270231880248,
"count": 8,
"is_parallel": true,
"self": 0.0009422270231880248
}
}
},
"UnityEnvironment.step": {
"total": 0.05068041500635445,
"count": 1,
"is_parallel": true,
"self": 0.00014139199629426003,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000927670014789328,
"count": 1,
"is_parallel": true,
"self": 0.000927670014789328
},
"communicator.exchange": {
"total": 0.048852696985704824,
"count": 1,
"is_parallel": true,
"self": 0.048852696985704824
},
"steps_from_proto": {
"total": 0.0007586560095660388,
"count": 1,
"is_parallel": true,
"self": 0.00016557800699956715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005930780025664717,
"count": 8,
"is_parallel": true,
"self": 0.0005930780025664717
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 265.46852942579426,
"count": 6317,
"is_parallel": true,
"self": 1.0132971906277817,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.356598369020503,
"count": 6317,
"is_parallel": true,
"self": 5.356598369020503
},
"communicator.exchange": {
"total": 252.42190109810326,
"count": 6317,
"is_parallel": true,
"self": 252.42190109810326
},
"steps_from_proto": {
"total": 6.6767327680427115,
"count": 6317,
"is_parallel": true,
"self": 1.319251311419066,
"children": {
"_process_rank_one_or_two_observation": {
"total": 5.3574814566236455,
"count": 50536,
"is_parallel": true,
"self": 5.3574814566236455
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 44.62049833574565,
"count": 6318,
"self": 0.14018061952083372,
"children": {
"process_trajectory": {
"total": 6.464301612315467,
"count": 6318,
"self": 6.464301612315467
},
"_update_policy": {
"total": 38.01601610390935,
"count": 34,
"self": 19.734592373570194,
"children": {
"TorchPPOOptimizer.update": {
"total": 18.281423730339156,
"count": 4566,
"self": 18.281423730339156
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.110050551593304e-07,
"count": 1,
"self": 5.110050551593304e-07
},
"TrainerController._save_models": {
"total": 0.17458409001119435,
"count": 1,
"self": 0.0004309089854359627,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17415318102575839,
"count": 1,
"self": 0.17415318102575839
}
}
}
}
}
}
}