LunarLander-v2_DeepRL
LunarLander-v2_DeepRL copied to clipboard
gym gymnasium compatibility issue?
hi daniel, i am working on irl, and wanted to just use your saved model to generate expert trajectories, but seems you have saved a model that is just trained on 100 episodes.. i thought to mitigate this by training again your model, but i get a problem about ---> 16 self.state_buffer[idx] = state 17 self.action_buffer[idx] = action 18 self.reward_buffer[idx] = reward
ValueError: setting an array element with a sequence. The requested array would exceed the maximum number of dimension of 1.
i am running the example in colab with gymnasium (hence maybe the samples are of different type), locally through the requirements file i had errors..