Generalization over Environments in Reinforcement Learning
نویسندگان
چکیده
منابع مشابه
Generalization over Environments in Reinforcement Learning
We give a method to optimize single-agent behavior for several environments and reinforcement functions by learning in several environments simultaneously in [5]. Now we address the problem of learning in one and applying the policy obtained to other environments. We discuss the influence of the environment on the ability to generalize over other environments. How do good learning environments ...
متن کاملGeneralization in Reinforcement Learning
In this paper we evaluate two Temporal Difference Reinforcement Learning methods on several different tasks to see how well these methods generalize. The tasks were modeled as Markov Decision Processes with a continuous observation space and a discrete action space. Function approximation was done using linear gradient descent with RBFs as features. The tasks were taken from the Polyathlon doma...
متن کاملGeneralization and Scaling in Reinforcement Learning
In associative reinforcement learning, an environment generates input vectors, a learning system generates possible output vectors, and a reinforcement function computes feedback signals from the input-output pairs. The task is to discover and remember input-output pairs that generate rewards. Especially difficult cases occur when rewards are rare, since the expected time for any algorithm can ...
متن کاملTowards Min Max Generalization in Reinforcement Learning
In this paper, we introduce a min max approach for addressing the generalization problem in Reinforcement Learning. The min max approach works by determining a sequence of actions that maximizes the worst return that could possibly be obtained considering any dynamics and reward function compatible with the sample of trajectories and some prior knowledge on the environment. We consider the part...
متن کاملGeneralization and Specialization in Reinforcement Learning
To learn efficiently, it is important that previous experiences can be used to select actions that have been successful in the past when new tasks are learned. We explore how generalization from previous training instances can be used to explore an action space in a more efficient way using ContextQ, which is an algorithm that learn to perform action in a particular context by generalizing maxi...
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: INTELIGENCIA ARTIFICIAL
سال: 2003
ISSN: 1988-3064,1137-3601
DOI: 10.4114/ia.v7i21.821