Investigating Simple Object Representations in Model-Free Deep Reinforcement Learning

2020-02-16 · Guy Davidson, Brenden M. Lake

We explore the benefits of augmenting state-of-the-art model-free deep reinforcement algorithms with simple object representations. Following the Frostbite challenge posited by Lake et al. (2017), we identify object representations as a critical cognitive capacity lacking from current reinforcement learning agents. We discover that providing the Rainbow model (Hessel et al.,2018) with simple, feature-engineered object representations substantially boosts its performance on the Frostbite game from Atari 2600. We then analyze the relative contributions of the representations of different types of objects, identify environment states where these representations are most impactful, and examine how these representations aid in generalizing to novel situations.

📄 PDF Abstract BibTeX arXiv:2002.06703

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningObjectreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning Sparse Representations in Reinforcement Learning with Sparse Coding

2017-07-26 · Lei Le, Raksha Kumaraswamy, Martha White

A variety of representation learning approaches have been investigated for reinforcement learning; much less attention, however, has been given to investigating the utility of sparse coding. Outside of reinforcement lear…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Representation Learning

Investigating the Properties of Neural Network Representations in Reinforcement Learning

2022-03-30 · Han Wang, Erfan Miahi, Martha White, Marlos C. Machado 외

In this paper we investigate the properties of representations learned by deep reinforcement learning systems. Much of the early work on representations for reinforcement learning focused on designing fixed-basis archite…

Deep Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+2

Interpreting Emergent Planning in Model-Free Reinforcement Learning

2025-04-02 · Thomas Bush, Stephen Chung, Usman Anwar, Adrià Garriga-Alonso 외

We present the first mechanistic evidence that model-free reinforcement learning agents can learn to plan. This is achieved by applying a methodology based on concept-based interpretability to a model-free agent in Sokob…

reinforcement-learning Reinforcement Learning Sokoban

One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHF

2025-03-25 · Xin Cai

In this article, we primarily examine a variety of RL-based and RL-free methods designed to address Reinforcement Learning from Human Feedback (RLHF) and Large Reasoning Models (LRMs). We begin with a concise overview of…

All reinforcement-learning Reinforcement Learning

Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice

2024-05-19 · Yusheng Jiao, Feng Ling, Sina Heydari, Nicolas Heess 외

Animals and robots exist in a physical world and must coordinate their bodies to achieve behavioral objectives. With recent developments in deep reinforcement learning, it is now possible for scientists and engineers to …

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning