Related papers: REX: Rapid Exploration and eXploitation for AI Age…
Proximal Policy Optimization with Adaptive Exploration (axPPO) is introduced as a novel learning algorithm. This paper investigates the exploration-exploitation tradeoff within the context of reinforcement learning and aims to contribute…
Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. While reinforcement learning (RL) has been shown to improve performance in this paradigm, its contributions remain…
We introduce Random Latent Exploration (RLE), a simple yet effective exploration strategy in reinforcement learning (RL). On average, RLE outperforms noise-based methods, which perturb the agent's actions, and bonus-based exploration, which…
Exploration is an essential component of reinforcement learning algorithms, where agents need to learn how to predict and control unknown and often stochastic environments. Reinforcement learning agents depend crucially on exploration to…
We present a new model-based algorithm for reinforcement learning (RL) which consists of explicit exploration and exploitation phases, and is applicable in large or infinite state spaces. The algorithm maintains a set of dynamics models…
One of the remaining challenges in reinforcement learning is to develop agents that can generalise to novel scenarios they might encounter once deployed. This challenge is often framed in a multi-task setting where agents train on a fixed…
Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation. Consequently, agents often converge to suboptimal policies…
Agentic retrieval-augmented generation (RAG) formulates question answering as a multi-step interaction between reasoning and information retrieval, and has recently been advanced by reinforcement learning (RL) with outcome-based…
Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…
Exploration is widely regarded as one of the most challenging aspects of reinforcement learning (RL), with many naive approaches succumbing to exponential sample complexity. To isolate the challenges of exploration, we propose a new…
Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic search remains…
To rapidly learn a new task, it is often essential for agents to explore efficiently -- especially when performance matters from the first timestep. One way to learn such behaviour is via meta-learning. Many existing methods however rely on…
Despite the fact that deep reinforcement learning (RL) has surpassed human-level performances in various tasks, it still has several fundamental challenges. First, most RL methods require intensive data from the exploration of the…
Sequential decision making problems, such as structured prediction, robotic control, and game playing, require a combination of planning policies and generalisation of those plans. In this paper, we present Expert Iteration (ExIt), a novel…
Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the significant human effort needed for their design and…
Model free reinforcement learning suffers from the high sampling complexity inherent to robotic manipulation or locomotion tasks. Most successful approaches typically use random sampling strategies which leads to slow policy convergence. In…
Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks. However, even state-of-the-art vision-language models (VLMs), such as GPT-4o, still fall short of human-level performance,…
Learning natural, animal-like locomotion from demonstrations has become a core paradigm in legged robotics. Despite the recent advancements in motion tracking, most existing methods demand extensive tuning and rely on reference data during…
Learning natural, animal-like locomotion from demonstrations has become a core paradigm in legged robotics. Despite the recent advancements in motion tracking, most existing methods demand extensive tuning and rely on reference data during…
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…