Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Jordan, Scott M."'
Novel reinforcement learning algorithms, or improvements on existing ones, are commonly justified by evaluating their performance on benchmark environments and are compared to an ever-changing set of standard algorithms. However, despite numerous cal
Externí odkaz:
http://arxiv.org/abs/2406.16241
This paper investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with learned models
Externí odkaz:
http://arxiv.org/abs/2406.01562
Autor:
Gupta, Dhawal, Jordan, Scott M., Chaudhari, Shreyas, Liu, Bo, Thomas, Philip S., da Silva, Bruno Castro
In this paper, we introduce a fresh perspective on the challenges of credit assignment and policy evaluation. First, we delve into the nuances of eligibility traces and explore instances where their updates may result in unexpected credit assignment
Externí odkaz:
http://arxiv.org/abs/2312.12972
Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that avoid inadve
Externí odkaz:
http://arxiv.org/abs/2310.19007
Autor:
Kostas, James E., Jordan, Scott M., Chandak, Yash, Theocharous, Georgios, Gupta, Dhawal, White, Martha, da Silva, Bruno Castro, Thomas, Philip S.
Coagent networks for reinforcement learning (RL) [Thomas and Barto, 2011] provide a powerful and flexible framework for deriving principled learning rules for arbitrary stochastic neural networks. The coagent framework offers an alternative to backpr
Externí odkaz:
http://arxiv.org/abs/2305.09838
Robust Markov Decision Processes (MDPs) are receiving much attention in learning a robust policy which is less sensitive to environment changes. There are an increasing number of works analyzing sample-efficiency of robust MDPs. However, there are tw
Externí odkaz:
http://arxiv.org/abs/2302.01248
Many real-world sequential decision-making problems involve critical systems with financial risks and human-life risks. While several works in the past have proposed methods that are safe for deployment, they assume that the underlying problem is sta
Externí odkaz:
http://arxiv.org/abs/2010.12645
Performance evaluations are critical for quantifying algorithmic advances in reinforcement learning. Recent reproducibility analyses have shown that reported performance results are often inconsistent and difficult to replicate. In this work, we argu
Externí odkaz:
http://arxiv.org/abs/2006.16958
We propose a new objective function for finite-horizon episodic Markov decision processes that better captures Bellman's principle of optimality, and provide an expression for the gradient of the objective.
Comment: 1 page, 0 figures
Comment: 1 page, 0 figures
Externí odkaz:
http://arxiv.org/abs/1906.03063
With the rise of neural models across the field of information retrieval, numerous publications have incrementally pushed the envelope of performance for a multitude of IR tasks. However, these networks often sample data in random order, are initiali
Externí odkaz:
http://arxiv.org/abs/1806.03790