Related papers: Ready Policy One: World Building Through Active Le…

Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved through prompt engineering or by aligning the task LLM itself,…

Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rely on unstructured self-sampling to fit scalar rewards, often producing inefficient rollouts…

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…

Reinforcement Learning (RL) has demonstrated a huge potential in learning optimal policies without any prior knowledge of the process to be controlled. Model Predictive Control (MPC) is a popular control technique which is able to deal with…

Achieving generalizable embodied policies remains a key challenge. Traditional policy learning paradigms, including both Imitation Learning (IL) and Reinforcement Learning (RL), struggle to cultivate generalizability across diverse…

Preference-based reinforcement learning (PbRL) has emerged as a promising approach for learning behaviors from human feedback without predefined reward functions. However, current PbRL methods face a critical challenge in effectively…

Intelligent agents must pursue their goals in complex environments with partial information and often limited computational capacity. Reinforcement learning methods have achieved great success by creating agents that optimize engineered…

Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from…

The Robust Markov Decision Process (RMDP) framework focuses on designing control policies that are robust against the parameter uncertainties due to the mismatches between the simulator model and real-world settings. An RMDP problem is…

Poor sample efficiency continues to be the primary challenge for deployment of deep Reinforcement Learning (RL) algorithms for real-world applications, and in particular for visuo-motor control. Model-based RL has the potential to be highly…

This paper presents a novel form of policy gradient for model-free reinforcement learning (RL) with improved exploration properties. Current policy-based methods use entropy regularization to encourage undirected exploration of the reward…

Multi-Objective Reinforcement Learning (MORL) is a generalization of traditional Reinforcement Learning (RL) that aims to optimize multiple, often conflicting objectives simultaneously rather than focusing on a single reward. This approach…

Model-based Reinforcement Learning (MBRL) is a promising framework for learning control in a data-efficient manner. MBRL algorithms can be fairly complex due to the separate dynamics modeling and the subsequent planning algorithm, and as a…

We present an adversarial active exploration for inverse dynamics model learning, a simple yet effective learning scheme that incentivizes exploration in an environment without any human intervention. Our framework consists of a deep…

Consider the following instance of the Offline Meta Reinforcement Learning (OMRL) problem: given the complete training logs of $N$ conventional RL agents, trained on $N$ different tasks, design a meta-agent that can quickly maximize reward…

Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters. It is particularly relevant for transferring policies learned in a simulation environment to…

It is still a challenging topic to make reactive driving behaviors in complex urban environments as road users' intentions are unknown. Model-based reinforcement learning (MBRL) offers great potential to learn a reactive policy by…

Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes…

Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance because agents fail to…

Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization.…