![]() This project develops a low-cost computer-based interactive system that generates a sense of deep engagement in the user, similar to that experienced when engaging with an artwork. Higher-complexity policies implement multi-modal strategies that compel the agent to seek power-ups and chase after vulnerable ghosts, both of which reduce the long-term costs. ![]() We show that low-complexity policies aim to only clear the environment of pellets while avoiding invulnerable ghosts. A major component of this paper is demonstrating that ranges of policy complexity values yield different game-play styles and analyzing why this occurs. We evaluate the performance of value-of-information-based policies on a stochastic version of Ms. A minimal-cost policy is sought in either case the obtainable cost depends on a single, tunable parameter that regulates the degree of policy complexity. As the policy complexity increases, the agents will take actions, regardless of the risk, that seek to decrease the long-term costs. The agents instead focus on simply completing their main objective in an expeditious fashion. As the policy complexity is reduced, there is a high chance that the agents will eschew risky actions that increase the long-term rewards. Our approach is based on the value of information, a criterion that provides an optimal trade-off between the expected return of a policy and the policy's complexity. In this paper, we consider an information-theoretic approach for performing constrained stochastic searches that promote the formation of risk-averse to risk-favoring behaviors. It can therefore be difficult to predict what agent behaviors might emerge. Conventional reinforcement learning methods for Markov decision processes rely on weakly-guided, stochastic searches to drive the learning process.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |