On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability
نویسندگان
چکیده
منابع مشابه
On overfitting and asymptotic bias in batch reinforcement learning with partial observability
This paper stands in the context of reinforcement learning with partial observability and limited data. In this setting, we focus on the tradeoff between asymptotic bias (suboptimality with unlimited data) and overfitting (additional suboptimality due to limited data), and theoretically show that while potentially increasing the asymptotic bias, a smaller state representation decreases the risk...
متن کاملConvergence Results for Reinforcement Learning with Partial Observability
In this report we propose two reinforcement learning algorithms developed to determine the optimal solution for Partially Observable Markov Decision Processes. The algorithms are analyzed and the corresponding convergence properties of both algorithms are established. Finally, both algorithms are tested in several examples from the literature and their performance is discussed. The lines for fu...
متن کاملOn Avoidance Learning with Partial Observability
We study a framework where agents have to avoid aversive signals. The agents are given only partial information, in the form of features that are projections of task states. Additionally, the agents have to cope with non-determinism, defined as unpredictability on the way that actions are executed. The goal of each agent is to define its behavior based on featureaction pairs that reliably avoid...
متن کاملManifold Embeddings for Model-Based Reinforcement Learning under Partial Observability
Interesting real-world datasets often exhibit nonlinear, noisy, continuous-valued states that are unexplorable, are poorly described by first principles, and are only partially observable. If partial observability can be overcome, these constraints suggest the use of model-based reinforcement learning. We experiment with manifold embeddings to reconstruct the observable state-space in the conte...
متن کاملBatch Reinforcement Learning
Batch reinforcement learning is a subfield of dynamic programming-based reinforcement learning. Originally defined as the task of learning the best possible policy from a fixed set of a priori-known transition samples, the (batch) algorithms developed in this field can be easily adapted to the classical online case, where the agent interacts with the environment while learning. Due to the effic...
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: Journal of Artificial Intelligence Research
سال: 2019
ISSN: 1076-9757
DOI: 10.1613/jair.1.11478