Parallel Reinforcement Learning Systems Using Exploration Agents

Guiding Reinforcement Learning Exploration Using Natural Language

In this work we present a technique to use natural language to help reinforcement learning generalize to unseen environments. This technique uses neural machine translation to learn associations between natural language behavior descriptions and state-action information. We then use this learned model to guide agent exploration to make it more effective at learning in unseen environments. We ev...

Reinforcement Learning with Exploration

Hierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents

This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...

Programmable Reinforcement Learning Agents

We present an expressive agent design language for reinforcement learning that allows the user to constrain the policies considered by the learning process.The language includes standard features such as parameterized subroutines, temporary interrupts, aborts, and memory variables, but also allows for unspecified choices in the agent program. For learning that which isn’t specified, we present ...

Efficient Exploration for Reinforcement Learning

Reinforcement learning is often regarded as one of the hardest problems in machine learning. Algorithms for solving these problems often require copious resources in comparison to other problems, and will often fail for no obvious reason. This report surveys a set of algorithms for various reinforcement learning problems that are known to terminate with good solution after a number of interacti...