Multi-Stage Episodic Control for Strategic Exploration in Text Games. (arXiv:2201.01251v1 [cs.CL])

Text adventure games present unique challenges to reinforcement learning
methods due to their combinatorially large action spaces and sparse rewards.
The interplay of these two factors is particularly demanding because large
action spaces require extensive exploration, while sparse rewards provide
limited feedback. This work proposes to tackle the explore-vs-exploit dilemma
using a multi-stage approach that explicitly disentangles these two strategies
within each episode. Our algorithm, called eXploit-Then-eXplore (XTX), begins
each episode using an exploitation policy that imitates a set of …

arxiv exploration games stage text