(MDP)
	gym-MiniGrid-MemoryS11-v0
(Agents)
	RLang-Dyna-Q-effect,0
	RLang-Dyna-Q-plan,1
	Dyna-Q,2
	Random,3
(Params)
	instances : 10
	episodes : 50
	steps : 500
	track_disc_reward : False
