gym.Env.reset() no longer returns observation of type np.array but a tuple of (observation, info)
AldairCB opened this issue · comments
Aldair Cuarez commented
A recent update to OpenAI Gym changed the way envs behave.
gym.Env.reset() now returns a tuple of (observation, info) so I think that every instance of observation = deepcopy(env.reset())
in keras-rl.rl.core.Agent.fit()
should be change to observation, info = deepcopy(env.reset())
.