Adaptation, Learning, and Optimization
Volume 1 / 2009 to Volume 27 / 2023
Page
%P
-
Article
Comparing explanations in RL
As deep reinforcement learning (RL)’s capabilities surpass traditional reinforcement learning, the community is working to make these black boxes less opaque. Explanations about algorithms’ choices and strateg...
-
Article
ASN: action semantics network for multiagent reinforcement learning
In multiagent systems (MASs), each agent makes individual decisions but all contribute globally to the system’s evolution. Learning in MASs is difficult since each agent’s selection of actions must take place ...
-
Article
Improving reinforcement learning with human assistance: an argument for human subject studies with HIPPO Gym
Reinforcement learning (RL) is a popular machine learning paradigm for game playing, robotics control, and other sequential decision tasks. However, RL agents often have long learning times with high data requ...
-
Article
hammer: Multi-level coordination of reinforcement learning agents via learned messaging
Cooperative multi-agent reinforcement learning (MARL) has achieved significant results, most notably by leveraging the representation-learning abilities of deep neural networks. However, large centralized appr...
-
Article
A conceptual framework for externally-influenced agents: an assisted reinforcement learning review
A long-term goal of reinforcement learning agents is to be able to perform tasks in complex real-world scenarios. The use of external information is one way of scaling agents to more complex problems. However,...
-
Book Series
-
Chapter and Conference Paper
C \(^{2}\) Tutor: Hel** People Learn to Avoid Present Bias During Decision Making
Procrastination can harm many aspects of life, including physical, mental, or financial well-being. It is often a consequence of people’s tendency to prefer immediate benefits over long-term rewards (i.e., pre...
-
Chapter
An Introduction to Federated and Transfer Learning
In today’s world, we have access to a tremendous amount of data. However, there is not enough high-quality data to obtain the desired results. More importantly, many industries have separate databases, with re...
-
Book
-
Article
Open AccessPolicy invariant explicit sha**: an efficient alternative to reward sha**
Reinforcement learning (RL) is a powerful learning paradigm in which agents can learn to maximize sparse and delayed reward signals. Although RL has had many impressive successes in complex domains, learning can ...
-
Article
Lucid dreaming for experience replay: refreshing past states with the current policy
Experience replay (ER) improves the data efficiency of off-policy reinforcement learning (RL) algorithms by allowing an agent to store and reuse its past experiences in a replay buffer. While many techniques h...
-
Chapter
Industry Applications
This chapter provides case studies for commercial applications of reinforcement learning as examples to learn from. We include brief descriptions of the core components needed to understand the problem and cur...
-
Chapter
Reinforcement Learning Theory
The previous chapter worked to explain the overall setting of reinforcement learning in MDPs. This chapter will introduce basic concepts about how a policy can be learned or improved over time. As in the previ...
-
Chapter
The Classroom Environment
We previously introduced the Robot Cleaner environment where probabilities were calculated based on trigonometry and distance equations. This chapter introduces the classroom environment and we show how to con...
-
Chapter
Conclusion
This book set out to introduce the approaches needing to understand how applying reinforcement learning might be achieved in practical real-world settings. To achieve this, we introduced the approach with defi...
-
Chapter
Background and Definitions
The ideas behind reinforcement learning date back to the 1950s. However, what we consider the “modern era” of reinforcement learning was kick-started in the mid-1990s [1, 14].
-
Book
-
Chapter
A Robot Cleaner Example
This example was created as a means to learn reinforcement learning independently in a Python notebook. Applying reinforcement learning without the need of a complex, virtual environment allows the reader to m...
-
Book and Conference Proceedings
Distributed Artificial Intelligence
Second International Conference, DAI 2020, Nan**g, China, October 24–27, 2020, Proceedings
-
Article
A survey and critique of multiagent deep reinforcement learning
Deep reinforcement learning (RL) has achieved outstanding results in recent years. This has led to a dramatic increase in the number of applications and methods. Recent works have explored learning beyond sing...
