Related papers: Perception-Prediction-Reaction Agents for Deep Rei…

Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the…

Humans are capable of attributing latent mental contents such as beliefs or intentions to others. The social skill is critical in daily life for reasoning about the potential consequences of others' behaviors so as to plan ahead. It is…

Inspired by the dual-process theory of human cognition from \textit{Thinking, Fast and Slow}, we introduce \textbf{PRIME} (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically…

The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are…

Recent advancements in large language models (LLMs) have enabled understanding webpage contexts, product details, and human instructions. Utilizing LLMs as the foundational architecture for either reward models or policies in reinforcement…

To effectively perform the task of next-word prediction, long short-term memory networks (LSTMs) must keep track of many types of information. Some information is directly related to the next word's identity, but some is more secondary…

Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on…

Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that…

Deep reinforcement learning (DRL) agents are trained through trial-and-error interactions with the environment. This leads to a long training time for dense neural networks to achieve good performance. Hence, prohibitive computation and…

Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…

Deep Reinforcement Learning (RL) is proven powerful for decision making in simulated environments. However, training deep RL model is challenging in real world applications such as production-scale health-care or recommender systems because…

We envision a continuous collaborative learning system where groups of LLM agents work together to solve reasoning problems, drawing on memory they collectively build to improve performance as they gain experience. This work establishes the…

We investigate the application of active inference in developing energy-efficient control agents for manufacturing systems. Active inference, rooted in neuroscience, provides a unified probabilistic framework integrating perception,…

Prioritized experience replay (PER) samples important transitions, rather than uniformly, to improve the performance of a deep reinforcement learning agent. We claim that such prioritization has to be balanced with sample diversity for…

Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in MLLM post-training for perception policy learning. While promising, our initial experiments reveal that incorporating a thinking…

Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. This model uses a soft, top-down attention mechanism to create a bottleneck in…

A growing body of evidence suggests that neural networks employed in deep reinforcement learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the analysis and mitigation of this phenomenon is hampered…

Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-policy algorithms such as PPO, GRPO, and REINFORCE++ serving as the dominant paradigm.…

Generating complex, logically-sound SPARQL queries for multi-hop questions remains a critical bottleneck for Knowledge Graph Question Answering, as the brittle nature of one-shot generation by Large Language Models (LLMs) hinders reliable…

Reinforcement Learning (RL) is a semi-supervised learning paradigm which an agent learns by interacting with an environment. Deep learning in combination with RL provides an efficient method to learn how to interact with the environment is…