problem "local variable 'policy_kwargsval' referenced before assignment" #34
Description
I am creating platformer game with RL agent. It is mario-like game, where AI player gets array of nearby tiles. This is 1D array with 90 elements (in my game i am transforming it into 2D (9,10) Array ).
I started really simple, but when got to moment when i starts MindMaker i got issue:
This is log from mindmaker console
(censored path)...Project\Content\MindMaker\dist\mindmaker\tensorboard\compat\tensorflow_stub\dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
MindMaker running, waiting for Unreal Engine to connect
(14476) wsgi starting up on http://0.0.0.0:3000
(14476) accepted ('127.0.0.1', 2927)
Connected To Unreal Engine
False
6
discrete action space
(censored path)...Project\Content\MindMaker\dist\mindmaker\gym\logger.py:30: UserWarning: ←[33mWARN: Box bound precision lowered by casting to float32←[0m
save model value: false
load model value: false
alg selected: PPO2
use custom: true
Exception in thread Thread-4:
Traceback (most recent call last):
File "threading.py", line 926, in _bootstrap_inner
File "threading.py", line 870, in run
File "site-packages\socketio\server.py", line 679, in _handle_event_internal
File "site-packages\socketio\server.py", line 708, in _trigger_event
File "mindmaker.py", line 716, in recieve
UnboundLocalError: local variable 'policy_kwargsval' referenced before assignment
I also catch .json that is being sent to mindmaker server:
{
"observations": "[0,0]",
"trainepisodes": 1000,
"evalepisodes": 100,
"maxactions": 6,
"loadmodel": "false",
"savemodel": "false",
"algselected": "PPO2",
"customparams": "true",
"modelname": "platformer_game_ai_model",
"conactionspace": false,
"done": false,
"actionspace": "6",
"observationspace": "low=np.zeros(90), high=np.full(90,10), dtype=np.float32",
"disactionspace": true,
"a2cparams": {
"gamma": 0.9900000095367432,
"n_steps": 5,
"vf_coef": 0.25,
"ent_coef": 0.009999999776482582,
"max_grad_norm": 0.05000000074505806,
"learning_rate": 0.000699999975040555,
"alpha": 0.9900000095367432,
"epsilon": 9.999999747378752e-06,
"lr_schedule": "constant",
"verbose": 0,
"tensorboard_log": "None",
"_init_setup_model": "True",
"full_tensorboard_log": "False",
"seed": "None",
"n_cpu_tf_sess": "None",
"network_arch": "[8, 'lstm', 64, 32]",
"act_func": 0,
"policy": 0
},
"acerparams": {
"gamma": 0.9900000095367432,
"n_steps": 5,
"ent_coef": 0.009999999776482582,
"max_grad_norm": 10,
"learning_rate": 0.000699999975040555,
"alpha": 0.9900000095367432,
"lr_schedule": "linear",
"verbose": 1,
"num_procs": "None",
"tensorboard_log": "None",
"_init_setup_model": "True",
"full_tensorboard_log": "False",
"seed": "None",
"n_cpu_tf_sess": "1",
"network_arch": "[64, 64, 32]",
"rprop_alpha": 0.9900000095367432,
"q_coef": 0.5,
"rprop_epsilon": 4.999999873689376e-05,
"buffer_size": 5000,
"replay_ratio": 4,
"replay_start": 1000,
"correction_term": 10,
"trust_region": "True",
"delta": 1,
"act_func": 0,
"policy": 0
},
"acktrparams": {
"gamma": 0.9900000095367432,
"n_steps": 5,
"ent_coef": 0.009999999776482582,
"max_grad_norm": 0.5,
"learning_rate": 0.25,
"lr_schedule": "linear",
"verbose": 1,
"tensorboard_log": "None",
"_init_setup_model": "True",
"full_tensorboard_log": "False",
"seed": "None",
"n_cpu_tf_sess": "1",
"network_arch": "[64, 64, 32]",
"nprocs": "None",
"vf_coef": 0.25,
"vf_fisher_coef": 1,
"kfac_clip": 0.0010000000474974513,
"async_eigen_decomp": "False",
"kfac_update": 0,
"gae_lambda": "None",
"act_func": 0,
"policy": 0
},
"dqnparams": {
"learning_rate": 0.0005000000237487257,
"verbose": 1,
"tensorboard_log": "None",
"_init_setup_model": "True",
"full_tensorboard_log": "False",
"seed": "None",
"n_cpu_tf_sess": "1",
"layers": "[64, 64]",
"buffer_size": "50000",
"exploration_fraction": 0.10000000149011612,
"exploration_final_eps": 0.019999999552965164,
"exploration_initial_eps": 1,
"train_freq": 1,
"batch_size": 32,
"double_q": "True",
"learning_starts": 100,
"target_network_update_freq": 500,
"prioritized_replay": "False",
"prioritized_replay_alpha": 0.6000000238418579,
"prioritized_replay_beta0": 0.4000000059604645,
"prioritized_replay_beta_iters": "None",
"prioritized_replay_eps": 6.000000212225132e-06,
"param_noise": "False",
"act_func": 0,
"policy": 0,
"gamma": 0.9900000095367432
},
"ppo2params": {
"gamma": 0.9900000095367432,
"verbose": 1,
"tensorboard_log": "None",
"_init_setup_model": "True",
"full_tensorboard_log": "False",
"seed": "None",
"n_cpu_tf_sess": "None",
"layers": "[64, 64]",
"lam": 0.949999988079071,
"n_steps": 128,
"ent_coef": 0.009999999776482582,
"learning_rate": 0.0002500000118743628,
"vf_coef": 0.5,
"max_grad_norm": 0.5,
"nminibatches": 4,
"noptepochs": 4,
"cliprange": 0.20000000298023224,
"cliprange_vf": "None",
"act_func": 0,
"policy": 0
},
"sacparams": {
"gamma": 0.9900000095367432,
"learning_rate": 0.0003000000142492354,
"verbose": 1,
"tensorboard_log": "None",
"_init_setup_model": "True",
"full_tensorboard_log": "False",
"seed": "None",
"n_cpu_tf_sess": "None",
"layers": "[64, 64]",
"buffer_size": "50000",
"train_freq": 1,
"batch_size": 64,
"learning_starts": 100,
"tau": 0.004999999888241291,
"ent_coef": "auto",
"target_update_interval": 1,
"gradient_steps": 1,
"target_entropy": "auto",
"action_noise": "None",
"random_exploration": 0,
"act_func": 0,
"policy": 0
},
"td3params": {
"gamma": 0.9900000095367432,
"learning_rate": 0.0003000000142492354,
"verbose": 1,
"tensorboard_log": "None",
"_init_setup_model": "True",
"full_tensorboard_log": "False",
"seed": "None",
"n_cpu_tf_sess": "None",
"layers": "[64, 64]",
"buffer_size": 50000,
"train_freq": 100,
"batch_size": 128,
"learning_starts": 100,
"tau": 0.004999999888241291,
"gradient_steps": 100,
"action_noise": "None",
"random_exploration": 0,
"policy_delay": 2,
"target_policy_noise": 0.20000000298023224,
"target_noise_clip": 0.5,
"act_func": 0,
"policy": 0
},
"reward": 0
}
tbh i need this to graduate my studies, so help would be welcome