Shaping Attention With Reward
نویسندگان
چکیده
منابع مشابه
Shaping attention with reward: effects of reward on space- and object-based selection.
The contribution of rewarded actions to automatic attentional selection remains obscure. We hypothesized that some forms of automatic orienting, such as object-based selection, can be completely abandoned in favor of a reward-maximizing strategy. In the two experiments reported here, we presented identical visual stimuli to observers while manipulating what was being rewarded (targets in differ...
متن کاملReward Shaping by Demonstration
Potential-based reward shaping is a theoretically sound way of incorporating prior knowledge in a reinforcement learning setting. While providing flexibility for choosing the potential function, under certain conditions this method guarantees the convergence of the final policy, regardless of the properties of the potential function. However, this flexibility of choice may cause confusion when ...
متن کاملOff-Policy Reward Shaping with Ensembles
Potential-based reward shaping (PBRS) is an effective and popular technique to speed up reinforcement learning by leveraging domain knowledge. While PBRS is proven to always preserve optimal policies, its effect on learning speed is determined by the quality of its potential function, which, in turn, depends on both the underlying heuristic and the scale. Knowing which heuristic will prove effe...
متن کاملAttention Shaping*
The paper examines software risk management in a novel way in which managers address risks through sequential attention shaping and intervention. These risks represent incongruent states within and between the four components of Leavitt's model: task, structure, technology, and actors. Such a state can in the extreme case lead to a failure of developing or implementing the software, and thus to...
متن کاملPolicy Transfer using Reward Shaping
Transfer learning has proven to be a wildly successful approach for speeding up reinforcement learning. Techniques often use low-level information obtained in the source task to achieve successful transfer in the target task. Yet, a most general transfer approach can only assume access to the output of the learning algorithm in the source task, i.e. the learned policy, enabling transfer irrespe...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Psychological Science
سال: 2013
ISSN: 0956-7976,1467-9280
DOI: 10.1177/0956797613490743