ReLAX: Reinforcement Learning Agent Explainer for Arbitrary Predictive Models
Counterfactual examples (CFs) are one of the most popular methods for attaching post-hoc
explanations to machine learning (ML) models. However, existing CF generation methods …
explanations to machine learning (ML) models. However, existing CF generation methods …
Refuel: Exploring sparse features in deep reinforcement learning for fast disease diagnosis
This paper proposes REFUEL, a reinforcement learning method with two techniques:{\em
reward shaping} and {\em feature rebuilding}, to improve the performance of online symptom …
reward shaping} and {\em feature rebuilding}, to improve the performance of online symptom …
Belief reward shaping in reinforcement learning
O Marom, B Rosman - Proceedings of the AAAI conference on artificial …, 2018 - ojs.aaai.org
A key challenge in many reinforcement learning problems is delayed rewards, which can
significantly slow down learning. Although reward shaping has previously been introduced …
significantly slow down learning. Although reward shaping has previously been introduced …
Explain the explainer: Interpreting model-agnostic counterfactual explanations of a deep reinforcement learning agent
Counterfactual examples (CFs) are one of the most popular methods for attaching post hoc
explanations to machine learning models. However, existing CF generation methods either …
explanations to machine learning models. However, existing CF generation methods either …
[HTML][HTML] Reward criteria impact on the performance of reinforcement learning agent for autonomous navigation
In reinforcement learning, an agent takes action at every time step (follows a policy) in an
environment to maximize the expected cumulative reward. Therefore, the shaping of a …
environment to maximize the expected cumulative reward. Therefore, the shaping of a …
Bayesian controller fusion: Leveraging control priors in deep reinforcement learning for robotics
We present Bayesian Controller Fusion (BCF): a hybrid control strategy that combines the
strengths of traditional hand-crafted controllers and model-free deep reinforcement learning …
strengths of traditional hand-crafted controllers and model-free deep reinforcement learning …
Deep reinforcement learning and simulation as a path toward precision medicine
Traditionally, precision medicine involves classifying patients to identify subpopulations that
respond favorably to specific therapeutics. We pose precision medicine as a dynamic …
respond favorably to specific therapeutics. We pose precision medicine as a dynamic …
An introduction to reinforcement learning
EF Morales, JH Zaragoza - Decision Theory Models for Applications …, 2012 - igi-global.com
This chapter provides a concise introduction to Reinforcement Learning (RL) from a
machine learning perspective. It provides the required background to understand the …
machine learning perspective. It provides the required background to understand the …
Using goal-conditioned reinforcement learning with deep imitation to control robot arm in flexible flat cable assembly task
J Li, H Shi, KS Hwang - IEEE Transactions on Automation …, 2023 - ieeexplore.ieee.org
Leveraging reinforcement learning on high-precision decision-making in Robot Arm
assembly scenes is a desired goal in the industrial community. However, tasks like Flexible …
assembly scenes is a desired goal in the industrial community. However, tasks like Flexible …
Multi-objectivization and ensembles of shapings in reinforcement learning
Ensemble techniques are a powerful approach to creating better decision makers in
machine learning. Multiple decision makers are trained to solve a given task, grouped in an …
machine learning. Multiple decision makers are trained to solve a given task, grouped in an …