BEERL: Both Ends Explanations for Reinforcement Learning

BEERL: Both Ends Explanations for Reinforcement Learning

Deep Reinforcement Learning (RL) is a black-box method and is hard to understand because the agent employs a neural network (NN). To explain the behavior and decisions made by the agent, different eXplainable RL (XRL) methods are developed; for example, feature importance methods are applied to anal...

Full description

Bibliographic Details
Main Authors:	Ahmad Terra, Rafia Inam, Elena Fersman
Format:	Article
Language:	English
Published:	MDPI AG 2022-10-01
Series:	Applied Sciences
Subjects:	explainability deep reinforcement learning explainable reinforcement learning reward decomposition reward prioritization bias
Online Access:	https://www.mdpi.com/2076-3417/12/21/10947

Similar Items

Attributation Analysis of Reinforcement Learning-Based Highway Driver
by: Nikodem Pankiewicz, et al.
Published: (2022-11-01)

Intelligent Decision Making Based on the Combination of Deep Reinforcement Learning and an Influence Map
by: Xiaofeng Lu, et al.
Published: (2022-11-01)

Learning Potential in Subgoal-Based Reward Shaping
by: Takato Okudo, et al.
Published: (2023-01-01)

Adaptive Reward Computation in Reinforcement Learning-Based Continuous Integration Testing
by: Yang Yang, et al.
Published: (2021-01-01)

Enhancing Efficiency in Hierarchical Reinforcement Learning through Topological-Sorted Potential Calculation
by: Ziyun Zhou, et al.
Published: (2023-09-01)

Explaining robot policies
by: Olivia Watkins, et al.
Published: (2021-12-01)

Benchmarking Perturbation-Based Saliency Maps for Explaining Atari Agents
by: Tobias Huber, et al.
Published: (2022-07-01)

Effects of dopamine on reinforcement learning and consolidation in Parkinson’s disease
by: John P Grogan, et al.
Published: (2017-07-01)

Cyberspace attack and defense game based on reward randomization reinforcement learning
by: Lei Zhang, et al.
Published: (2022-12-01)

Rewards Prediction-Based Credit Assignment for Reinforcement Learning With Sparse Binary Rewards
by: Minah Seo, et al.
Published: (2019-01-01)

Average reward rates enable motivational transfer across independent reinforcement learning tasks
by: Kristoffer C. Aberg, et al.
Published: (2022-11-01)

GR(1)-Guided Deep Reinforcement Learning for Multi-Task Motion Planning under a Stochastic Environment
by: Chenyang Zhu, et al.
Published: (2022-11-01)

Reinforcement biases subsequent perceptual decisions when confidence is low, a widespread behavioral phenomenon
by: Armin Lak, et al.
Published: (2020-04-01)

Boosting Policy Learning in Reinforcement Learning via Adaptive Intrinsic Reward Regulation
by: Qian Zhao, et al.
Published: (2024-01-01)

Implementasi Sistem Kendali Keseimbangan Statis Pada Robot Quadruped Menggunakan Reinforcement Learning
by: Hidayat Eko Saputro, et al.
Published: (2023-04-01)

An Evaluation Methodology for Interactive Reinforcement Learning with Simulated Users
by: Adam Bignold, et al.
Published: (2021-02-01)

Subgoal-Based Reward Shaping to Improve Efficiency in Reinforcement Learning
by: Takato Okudo, et al.
Published: (2021-01-01)

Reward Shaping Based Federated Reinforcement Learning
by: Yiqiu Hu, et al.
Published: (2021-01-01)

The Straw That Broke the Camel’s Back: Natural Variations in 17β-Estradiol and COMT-Val158Met Genotype Interact in the Modulation of Model-Free and Model-Based Control
by: Esther K. Diekhof, et al.
Published: (2021-07-01)

Deep Reinforcement Learning With Optimized Reward Functions for Robotic Trajectory Planning
by: Jiexin Xie, et al.
Published: (2019-01-01)

Pleasurable music affects reinforcement learning according to the listener
by: Benjamin P Gold, et al.
Published: (2013-08-01)

Financial portfolio optimization: an autoregressive deep reinforcement learning algorithm with learned intrinsic rewards
by: Lim, Magdalene Hui Qi
Published: (2024)

A study on deep reinforcement learning-based crane scheduling model for uncertainty tasks
by: Feng Kai, et al.
Published: (2022-08-01)

Explainable AI and Reinforcement Learning—A Systematic Review of Current Approaches and Trends
by: Lindsay Wells, et al.
Published: (2021-05-01)

Reward-weighted DHER Mechanism For Multi-goal Reinforcement Learning With Application To Robotic Manipulation Control
by: Xueyu Wei, et al.
Published: (2023-08-01)

Hierarchical Reinforcement Learning Framework in Geographic Coordination for Air Combat Tactical Pursuit
by: Ruihai Chen, et al.
Published: (2023-10-01)

Noise-Correlation Is Modulated by Reward Expectation in the Primary Motor Cortex Bilaterally During Manual and Observational Tasks in Primates
by: Brittany Moore, et al.
Published: (2020-12-01)

Multiobjective Reinforcement Learning Based Energy Consumption in C-RAN enabled Massive MIMO
by: S. Sharma, et al.
Published: (2022-04-01)

Explaining the Behaviour of Reinforcement Learning Agents in a Multi-Agent Cooperative Environment Using Policy Graphs
by: Marc Domenech i Vila, et al.
Published: (2024-01-01)

Adaptive Reward Method for End-to-End Cooperation Based on Multi-agent Reinforcement Learning
by: SHI Dian-xi, ZHAO Chen-ran, ZHANG Yao-wen, YANG Shao-wu, ZHANG Yong-jun
Published: (2022-08-01)

Leveraging Minimum Nodes for Optimum Key Player Identification in Complex Networks: A Deep Reinforcement Learning Strategy with Structured Reward Shaping
by: Li Zeng, et al.
Published: (2023-08-01)

Explaining a Deep Reinforcement Learning (DRL)-Based Automated Driving Agent in Highway Simulations
by: Francesco Bellotti, et al.
Published: (2023-01-01)

Efficient state representation with artificial potential fields for reinforcement learning
by: Hao Jiang, et al.
Published: (2023-02-01)

Reinforcement Learning in Autism Spectrum Disorder
by: Manuela Schuetze, et al.
Published: (2017-11-01)

The Control Method of Twin Delayed Deep Deterministic Policy Gradient with Rebirth Mechanism to Multi-DOF Manipulator
by: Yangyang Hou, et al.
Published: (2021-04-01)

Learning Reward Function with Matching Network for Mapless Navigation
by: Qichen Zhang, et al.
Published: (2020-06-01)

Explaining Deep Q-Learning Experience Replay with SHapley Additive exPlanations
by: Robert S. Sullivan, et al.
Published: (2023-10-01)

Learning to Utilize Curiosity: A New Approach of Automatic Curriculum Learning for Deep RL
by: Zeyang Lin, et al.
Published: (2022-07-01)

Iterative Oblique Decision Trees Deliver Explainable RL Models
by: Raphael C. Engelhardt, et al.
Published: (2023-05-01)

Automated Hyperparameter Tuning in Reinforcement Learning for Quadrupedal Robot Locomotion
by: MyeongSeop Kim, et al.
Published: (2023-12-01)