|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.6236514449119568, |
|
"min": 0.6221056580543518, |
|
"max": 1.3724123239517212, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 18569.845703125, |
|
"min": 18569.845703125, |
|
"max": 41633.5, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989935.0, |
|
"min": 29952.0, |
|
"max": 989935.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989935.0, |
|
"min": 29952.0, |
|
"max": 989935.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.38827192783355713, |
|
"min": -0.11228569597005844, |
|
"max": 0.46265578269958496, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 104.83341979980469, |
|
"min": -27.06085205078125, |
|
"max": 122.6037826538086, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.04411130025982857, |
|
"min": -0.044483501464128494, |
|
"max": 0.26989611983299255, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -11.910051345825195, |
|
"min": -11.910051345825195, |
|
"max": 65.04496765136719, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06687907542564113, |
|
"min": 0.06457956099288578, |
|
"max": 0.07331588846806832, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9363070559589759, |
|
"min": 0.5132112192764782, |
|
"max": 1.05867257450568, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.012840779270341388, |
|
"min": 0.0005707512971639515, |
|
"max": 0.014266884304324318, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.17977090978477944, |
|
"min": 0.008561269457459273, |
|
"max": 0.19973638026054044, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.466218939864285e-06, |
|
"min": 7.466218939864285e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0001045270651581, |
|
"min": 0.0001045270651581, |
|
"max": 0.0036335182888272994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10248870714285715, |
|
"min": 0.10248870714285715, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4348419000000001, |
|
"min": 1.3886848, |
|
"max": 2.611172700000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002586218435714286, |
|
"min": 0.0002586218435714286, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0036207058100000003, |
|
"min": 0.0036207058100000003, |
|
"max": 0.12113615272999997, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.00835470575839281, |
|
"min": 0.00832738820463419, |
|
"max": 0.35373637080192566, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1169658750295639, |
|
"min": 0.1165834367275238, |
|
"max": 2.4761545658111572, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 454.79411764705884, |
|
"min": 410.05797101449275, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30926.0, |
|
"min": 15984.0, |
|
"max": 32561.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.3098176198408884, |
|
"min": -1.0000000521540642, |
|
"max": 1.5029651926479477, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 89.06759814918041, |
|
"min": -29.960001669824123, |
|
"max": 103.7045982927084, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.3098176198408884, |
|
"min": -1.0000000521540642, |
|
"max": 1.5029651926479477, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 89.06759814918041, |
|
"min": -29.960001669824123, |
|
"max": 103.7045982927084, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.03982307824416614, |
|
"min": 0.03704946053524812, |
|
"max": 7.219425258226693, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.707969320603297, |
|
"min": 2.5039204622153193, |
|
"max": 115.51080413162708, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1660189310", |
|
"python_version": "3.9.12 (main, Jun 1 2022, 11:38:51) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/home/johneblake/miniconda3/envs/sb/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", |
|
"mlagents_version": "0.29.0", |
|
"mlagents_envs_version": "0.29.0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1660192123" |
|
}, |
|
"total": 2812.2159062640003, |
|
"count": 1, |
|
"self": 0.6270798320010726, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.02901312899939512, |
|
"count": 1, |
|
"self": 0.02901312899939512 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2811.559813303, |
|
"count": 1, |
|
"self": 1.5933887450237307, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.772386546999769, |
|
"count": 1, |
|
"self": 6.772386546999769 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2802.9082381799763, |
|
"count": 63581, |
|
"self": 1.4503929650254577, |
|
"children": { |
|
"env_step": { |
|
"total": 1737.238073262034, |
|
"count": 63581, |
|
"self": 1491.761737549191, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 244.47304408992022, |
|
"count": 63581, |
|
"self": 5.597185046764025, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 238.8758590431562, |
|
"count": 62548, |
|
"self": 118.71025110914525, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 120.16560793401095, |
|
"count": 62548, |
|
"self": 120.16560793401095 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.0032916229229158, |
|
"count": 63581, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2807.6762133979764, |
|
"count": 63581, |
|
"is_parallel": true, |
|
"self": 1426.942226425016, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0016280949994325056, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005332719993020874, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0010948230001304182, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0010948230001304182 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04130141699988599, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00037018299917690456, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00028980600018257974, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00028980600018257974 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.039464326000597794, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.039464326000597794 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0011771019999287091, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0002989370013892767, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008781649985394324, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0008781649985394324 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1380.7339869729603, |
|
"count": 63580, |
|
"is_parallel": true, |
|
"self": 24.83135168610079, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 18.57734280796012, |
|
"count": 63580, |
|
"is_parallel": true, |
|
"self": 18.57734280796012 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1261.8286872870212, |
|
"count": 63580, |
|
"is_parallel": true, |
|
"self": 1261.8286872870212 |
|
}, |
|
"steps_from_proto": { |
|
"total": 75.49660519187819, |
|
"count": 63580, |
|
"is_parallel": true, |
|
"self": 19.05568535395105, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 56.44091983792714, |
|
"count": 508640, |
|
"is_parallel": true, |
|
"self": 56.44091983792714 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1064.2197719529167, |
|
"count": 63581, |
|
"self": 2.8506866588832054, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 203.97335532303987, |
|
"count": 63581, |
|
"self": 203.43294572703962, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.5404095960002451, |
|
"count": 2, |
|
"self": 0.5404095960002451 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 857.3957299709937, |
|
"count": 454, |
|
"self": 228.09340281389268, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 629.302327157101, |
|
"count": 22815, |
|
"self": 629.302327157101 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.800005500437692e-07, |
|
"count": 1, |
|
"self": 9.800005500437692e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.2857988509995266, |
|
"count": 1, |
|
"self": 0.054588397999395966, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.23121045300013066, |
|
"count": 1, |
|
"self": 0.23121045300013066 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |