Semi-Supervised Policy Initialization for Playing Games with Language Hints

Using natural language as a hint can supply an additional reward for playing sparse-reward games. Achieving a goal should involve several different hints, while the given hints are usually incomplete. Those unmentioned latent hints still rely on the sparse reward signal, and make the learning process difficult. In this paper, we propose semi-supervised initialization (SSI) that allows the agent to learn from various possible hints before training under different tasks. Experiments show that SSI not only helps to learn faster (1.2x) but also has a higher success rate (11% relative improvement) of the final policy.