Open davidhennemann opened 2 years ago
in training_scenario.py in train_from_config() the RL config seems to be hardcoded to q_learning_config.
training_scenario.py
train_from_config()
q_learning_config
config_rl: AttrDict = HyperparameterConfigLoader.load('q_learning_config', config_environment.agent[0]['agent_class'])
According to the wiki the relevant config file should be named rl_config.json . The same issue can also be found in the exampleprinter.py.
rl_config.json
exampleprinter.py
in
training_scenario.py
intrain_from_config()
the RL config seems to be hardcoded toq_learning_config
.According to the wiki the relevant config file should be named
rl_config.json
. The same issue can also be found in theexampleprinter.py
.