Related papers: MADE: Exploration via Maximizing Deviation from Ex…
Autonomous navigation in crowded environments is an open problem with many applications, essential for the coexistence of robots and humans in the smart cities of the future. In recent years, deep reinforcement learning approaches have…
The upper confidence reinforcement learning (UCRL2) algorithm introduced in (Jaksch et al., 2010) is a popular method to perform regret minimization in unknown discrete Markov Decision Processes under the average-reward criterion. Despite…
Reinforcement learning (RL) has achieved promising results on most robotic control tasks. Safety of learning-based controllers is an essential notion of ensuring the effectiveness of the controllers. Current methods adopt whole consistency…
Efficient exploration is necessary to achieve good sample efficiency for reinforcement learning in general. From small, tabular settings such as gridworlds to large, continuous and sparse reward settings such as robotic object manipulation…
In many real-world applications of reinforcement learning (RL), performing actions requires consuming certain types of resources that are non-replenishable in each episode. Typical applications include robotic control with limited energy…
The goal of continuous control is to synthesize desired behaviors. In reinforcement learning (RL)-driven approaches, this is often accomplished through careful task reward engineering for efficient exploration and running an off-the-shelf…
Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks. Despite recent progress, efficient exploration in meta-RL remains a key challenge in sparse-reward tasks, as it requires…
We study reward-free and reward-agnostic exploration in episodic finite-horizon Markov decision processes (MDPs), where an agent explores an unknown environment without observing external rewards. Reward-free exploration aims to enable…
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…
Model-based Reinforcement Learning (MBRL) has emerged as a promising paradigm for autonomous driving, where data efficiency and robustness are critical. Yet, existing solutions often rely on carefully crafted, task specific extrinsic…
One of the challenges in online reinforcement learning (RL) is that the agent needs to trade off the exploration of the environment and the exploitation of the samples to optimize its behavior. Whether we optimize for regret, sample…
Reinforcement learning (RL) is one of the three basic paradigms of machine learning. It has demonstrated impressive performance in many complex tasks like Go and StarCraft, which is increasingly involved in smart manufacturing and…
Exploration is fundamental to reinforcement learning (RL), as it determines how effectively an agent discovers and exploits the underlying structure of its environment to achieve optimal performance. Existing exploration methods generally…
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…
Exploration is essential in reinforcement learning as an agent relies on trial and error to learn an optimal policy. However, when rewards are sparse, naive exploration strategies, like noise injection, are often insufficient. Intrinsic…
Model-based reinforcement learning algorithms with probabilistic dynamical models are amongst the most data-efficient learning methods. This is often attributed to their ability to distinguish between epistemic and aleatoric uncertainty.…
The inherent uncertainty in the environmental transition model of Reinforcement Learning (RL) necessitates a delicate balance between exploration and exploitation. This balance is crucial for optimizing computational resources to accurately…
Intrinsic rewards play a central role in handling the exploration-exploitation trade-off when designing sequential decision-making algorithms, in both foundational theory and state-of-the-art deep reinforcement learning. The LinUCB…
We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…
Meta-Black-Box Optimization (MetaBBO) is an emerging avenue within Optimization community, where algorithm design policy could be meta-learned by reinforcement learning to enhance optimization performance. So far, the reward functions in…