|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.49954187870025635, |
|
"min": 0.4777816832065582, |
|
"max": 1.363349437713623, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 14946.29296875, |
|
"min": 14295.2275390625, |
|
"max": 41358.5703125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479931.0, |
|
"min": 29989.0, |
|
"max": 479931.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479931.0, |
|
"min": 29989.0, |
|
"max": 479931.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.05493435263633728, |
|
"min": -0.08929532766342163, |
|
"max": 0.11173196882009506, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -13.294113159179688, |
|
"min": -21.520174026489258, |
|
"max": 26.592208862304688, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.020537864416837692, |
|
"min": 0.015147145837545395, |
|
"max": 0.32631510496139526, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.970163345336914, |
|
"min": 3.665609359741211, |
|
"max": 78.64193725585938, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.067007277642242, |
|
"min": 0.06495651438137216, |
|
"max": 0.07468566069547297, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.938101886991388, |
|
"min": 0.5789700971930497, |
|
"max": 0.9920040435034007, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0025039247564496337, |
|
"min": 0.0007112048412999796, |
|
"max": 0.008871167425956075, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.03505494659029487, |
|
"min": 0.009956867778199714, |
|
"max": 0.0709693394076486, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.0895735891928573e-05, |
|
"min": 2.0895735891928573e-05, |
|
"max": 0.00029044552818482494, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.000292540302487, |
|
"min": 0.000292540302487, |
|
"max": 0.003318377593874199, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10696521428571429, |
|
"min": 0.10696521428571429, |
|
"max": 0.196815175, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.497513, |
|
"min": 1.497513, |
|
"max": 2.4061258, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007058249071428572, |
|
"min": 0.0007058249071428572, |
|
"max": 0.009681835982500001, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.009881548700000001, |
|
"min": 0.009881548700000001, |
|
"max": 0.11063196741999999, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.018649527803063393, |
|
"min": 0.018649527803063393, |
|
"max": 0.4523535370826721, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2610933780670166, |
|
"min": 0.2610933780670166, |
|
"max": 3.618828296661377, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 950.0625, |
|
"min": 908.28125, |
|
"max": 993.3125, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30402.0, |
|
"min": 15893.0, |
|
"max": 33151.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.5755875497125089, |
|
"min": -0.9137643368116447, |
|
"max": -0.57160003833911, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -18.418801590800285, |
|
"min": -29.182201765477657, |
|
"max": -13.90800078958273, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.5755875497125089, |
|
"min": -0.9137643368116447, |
|
"max": -0.57160003833911, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -18.418801590800285, |
|
"min": -29.182201765477657, |
|
"max": -13.90800078958273, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.1821828501924756, |
|
"min": 0.1821828501924756, |
|
"max": 9.211093381978571, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.829851206159219, |
|
"min": 5.78629396064207, |
|
"max": 147.37749411165714, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 16 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1675948434", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics", |
|
"mlagents_version": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.21.6", |
|
"end_time_seconds": "1675949576" |
|
}, |
|
"total": 1141.979129558, |
|
"count": 1, |
|
"self": 0.5862056359999315, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.1217019400000936, |
|
"count": 1, |
|
"self": 0.1217019400000936 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1141.271221982, |
|
"count": 1, |
|
"self": 0.7270084210058485, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.224639921000062, |
|
"count": 1, |
|
"self": 6.224639921000062 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1134.225539800994, |
|
"count": 31593, |
|
"self": 0.7592975529930754, |
|
"children": { |
|
"env_step": { |
|
"total": 752.505427850002, |
|
"count": 31593, |
|
"self": 691.9375306370509, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 60.108942763976984, |
|
"count": 31593, |
|
"self": 2.3663719869800843, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 57.7425707769969, |
|
"count": 31308, |
|
"self": 19.33083116898706, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 38.41173960800984, |
|
"count": 31308, |
|
"self": 38.41173960800984 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.4589544489740547, |
|
"count": 31593, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1138.620222788013, |
|
"count": 31593, |
|
"is_parallel": true, |
|
"self": 506.0885998520471, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019544179999684275, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007022370002687239, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012521809996997035, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012521809996997035 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0480101040000136, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000533700999994835, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005103430000872322, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005103430000872322 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04528111199988416, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04528111199988416 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016849480000473704, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00042015000008177594, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012647979999655945, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012647979999655945 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 632.531622935966, |
|
"count": 31592, |
|
"is_parallel": true, |
|
"self": 16.095642684994573, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 11.66120515100988, |
|
"count": 31592, |
|
"is_parallel": true, |
|
"self": 11.66120515100988 |
|
}, |
|
"communicator.exchange": { |
|
"total": 554.8465329949834, |
|
"count": 31592, |
|
"is_parallel": true, |
|
"self": 554.8465329949834 |
|
}, |
|
"steps_from_proto": { |
|
"total": 49.92824210497815, |
|
"count": 31592, |
|
"is_parallel": true, |
|
"self": 11.507329051980605, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 38.42091305299755, |
|
"count": 252736, |
|
"is_parallel": true, |
|
"self": 38.42091305299755 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 380.960814397999, |
|
"count": 31593, |
|
"self": 1.3108012589880218, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 81.9100688430076, |
|
"count": 31593, |
|
"self": 81.80934747400761, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1007213689999844, |
|
"count": 1, |
|
"self": 0.1007213689999844 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 297.7399442960034, |
|
"count": 220, |
|
"self": 113.1725067469979, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 184.5674375490055, |
|
"count": 11370, |
|
"self": 184.5674375490055 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0050002856587525e-06, |
|
"count": 1, |
|
"self": 1.0050002856587525e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09403283399979045, |
|
"count": 1, |
|
"self": 0.0019365049997759343, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09209632900001452, |
|
"count": 1, |
|
"self": 0.09209632900001452 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |