Deep reinforcement learning (RL) methods often require many trials before convergence,
and no direct interpretability of trained policies is provided. In order to achieve fast …

Text Worlds are virtual environments for embodied agents that, unlike 2D or 3D
environments, are rendered exclusively using textual descriptions. These environments offer …

Reinforcement Learning has shown success in a number of complex virtual environments.
However, many challenges still exist towards solving problems with natural language as a …

Text-based reinforcement learning agents have predominantly been neural network-based
models with embeddings-based representation, learning uninterpretable policies that often …

Text-based games provide a framework for developing natural language understanding and
commonsense knowledge about the world in reinforcement learning based agents. Existing …

We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement
learning applications with a neuro-symbolic framework which is a combination of neural …

Text-based games (TBGs) have become a popular proving ground for the demonstration of
learning-based agents that make decisions in quasi real-world settings. The crux of the …

Model-based reinforcement learning has shown great results when using deep neural
networks for learning world models. However, these results are not directly applicable to …

Improving generalization in text-based games serves as a useful stepping-stone towards
reinforcement learning (RL) agents with generic linguistic ability. Data augmentation for …

Abstract Language-conditional reinforcement learning refers to the reinforcement learning
task where the language information serves as essential components in the problem …