Fast reinforcement learning with generalized policy updates
The combination of reinforcement learning with deep learning is a promising approach to
tackle important sequential decision-making problems that are currently intractable. One …
tackle important sequential decision-making problems that are currently intractable. One …
Approximate policy-based accelerated deep reinforcement learning
X Wang, Y Gu, Y Cheng, A Liu… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
In recent years, the deep reinforcement learning (DRL) algorithms have been developed
rapidly and have achieved excellent performance in many challenging tasks. However, due …
rapidly and have achieved excellent performance in many challenging tasks. However, due …
Multi-step reinforcement learning: A unifying algorithm
Unifying seemingly disparate algorithmic ideas to produce better performing algorithms has
been a longstanding goal in reinforcement learning. As a primary example, TD (λ) elegantly …
been a longstanding goal in reinforcement learning. As a primary example, TD (λ) elegantly …
Can increasing input dimensionality improve deep reinforcement learning?
Deep reinforcement learning (RL) algorithms have recently achieved remarkable successes
in various sequential decision making tasks, leveraging advances in methods for training …
in various sequential decision making tasks, leveraging advances in methods for training …
Using inaccurate models in reinforcement learning
In the model-based policy search approach to reinforcement learning (RL), policies are
found using a model (or" simulator") of the Markov decision process. However, for high …
found using a model (or" simulator") of the Markov decision process. However, for high …
Learning dynamics and generalization in deep reinforcement learning
Solving a reinforcement learning (RL) problem poses two competing challenges: fitting a
potentially discontinuous value function, and generalizing well to new observations. In this …
potentially discontinuous value function, and generalizing well to new observations. In this …
Dueling network architectures for deep reinforcement learning
In recent years there have been many successes of using deep representations in
reinforcement learning. Still, many of these applications use conventional architectures …
reinforcement learning. Still, many of these applications use conventional architectures …
Near optimal reward-free reinforcement learning
We study the reward-free reinforcement learning framework, which is particularly suitable for
batch reinforcement learning and scenarios where one needs policies for multiple reward …
batch reinforcement learning and scenarios where one needs policies for multiple reward …
Taxonomy of reinforcement learning algorithms
H Zhang, T Yu - Deep reinforcement learning: Fundamentals, research …, 2020 - Springer
In this chapter, we introduce and summarize the taxonomy and categories for reinforcement
learning (RL) algorithms. Figure 3.1 presents an overview of the typical and popular …
learning (RL) algorithms. Figure 3.1 presents an overview of the typical and popular …
[图书][B] Shaping and policy search in reinforcement learning
AY Ng - 2003 - search.proquest.com
To make reinforcement learning algorithms run in a reasonable amount of time, it is
frequently necessary to use a well-chosen reward function that gives appropriate “hints” to …
frequently necessary to use a well-chosen reward function that gives appropriate “hints” to …