On Transforming Reinforcement Learning With Transformers: The Development Trajectory

S Hu, L Shen, Y Zhang, Y Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Transformers, originally devised for natural language processing (NLP), have also produced
significant successes in computer vision (CV). Due to their strong expression power …

Interactive natural language processing

Z Wang, G Zhang, K Yang, N Shi, W Zhou… - arXiv preprint arXiv …, 2023 - arxiv.org
Interactive Natural Language Processing (iNLP) has emerged as a novel paradigm within
the field of NLP, aimed at addressing limitations in existing frameworks while aligning with …

Introspective tips: Large language model for in-context decision making

L Chen, L Wang, H Dong, Y Du, J Yan, F Yang… - arXiv preprint arXiv …, 2023 - arxiv.org
The emergence of large language models (LLMs) has substantially influenced natural
language processing, demonstrating exceptional results across various tasks. In this study …

NL2Color: Refining color palettes for charts with natural language

C Shi, W Cui, C Liu, C Zheng, H Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Choice of color is critical to creating effective charts with an engaging, enjoyable, and
informative reading experience. However, designing a good color palette for a chart is a …

Arigraph: Learning knowledge graph world models with episodic memory for llm agents

P Anokhin, N Semenov, A Sorokin, D Evseev… - arXiv preprint arXiv …, 2024 - arxiv.org
Advancements in generative AI have broadened the potential applications of Large
Language Models (LLMs) in the development of autonomous agents. Achieving true …

Learning belief representations for partially observable deep RL

A Wang, AC Li, TQ Klassen, RT Icarte… - International …, 2023 - proceedings.mlr.press
Many important real-world Reinforcement Learning (RL) problems involve partial
observability and require policies with memory. Unfortunately, standard deep RL algorithms …

EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning

K Basu, K Murugesan, S Chaudhury… - arXiv preprint arXiv …, 2024 - arxiv.org
Text-based games (TBGs) have emerged as an important collection of NLP tasks, requiring
reinforcement learning (RL) agents to combine natural language understanding with …

Noisy symbolic abstractions for deep RL: A case study with reward machines

AC Li, Z Chen, P Vaezipoor, TQ Klassen… - arXiv preprint arXiv …, 2022 - arxiv.org
Natural and formal languages provide an effective mechanism for humans to specify
instructions and reward functions. We investigate how to generate policies via RL when …

Reward Machines for Deep RL in Noisy and Uncertain Environments

AC Li, Z Chen, TQ Klassen, P Vaezipoor… - arXiv preprint arXiv …, 2024 - arxiv.org
Reward Machines provide an automata-inspired structure for specifying instructions, safety
constraints, and other temporally extended reward-worthy behaviour. By exposing complex …

[PDF][PDF] Using Incomplete and Incorrect Plans to Shape Reinforcement Learning in Long-Sequence Sparse-Reward Tasks

H Müller, D Kudenko - Proc. of the Adaptive and …, 2023 - alaworkshop2023.github.io
Reinforcement learning (RL) agents naturally struggle with longsequence sparse reward
tasks due to the lack of reward feedback during exploration and the problem of identifying …