Related papers: State-Augmentation Transformations for Risk-Sensit…
We introduce a novel framework to account for sensitivity to rewards uncertainty in sequential decision-making problems. While risk-sensitive formulations for Markov decision processes studied so far focus on the distribution of the…
We study infinite horizon Markov decision processes (MDPs) with "fast-slow" structure, where some state variables evolve rapidly ("fast states") while others change more gradually ("slow states"). This structure commonly arises in practice…
We propose a simple, practical, and intuitive approach for domain adaptation in reinforcement learning. Our approach stems from the idea that the agent's experience in the source domain should look similar to its experience in the target…
In dynamic programming (DP) and reinforcement learning (RL), an agent learns to act optimally in terms of expected long-term return by sequentially interacting with its environment modeled by a Markov decision process (MDP). More generally…
A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent…
In this paper, we propose a new solution to reward adaptation (RA) in reinforcement learning, where the agent adapts to a target reward function based on one or more existing source behaviors learned a priori under the same domain dynamics…
Reward-free reinforcement learning (RL) considers the setting where the agent does not have access to a reward function during exploration, but must propose a near-optimal policy for an arbitrary reward function revealed only after…
Reinforcement learning involves agents interacting with an environment to complete tasks. When rewards provided by the environment are sparse, agents may not receive immediate feedback on the quality of actions that they take, thereby…
One major limitation to the applicability of Reinforcement Learning (RL) to many practical domains is the large number of samples required to learn an optimal policy. To address this problem and improve learning efficiency, we consider a…
Safety in stochastic control systems, which are subject to random noise with a known probability distribution, aims to compute policies that satisfy predefined operational constraints with high confidence throughout the uncertain evolution…
We investigate model-based reinforcement learning in contextual Markov decision processes (C-MDPs) in which the context is unobserved and induces confounding in the offline dataset. In such settings, conventional model-learning methods are…
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…
We report a previously unidentified issue with model-free, value-based approaches to multiobjective reinforcement learning in the context of environments with stochastic state transitions. An example multiobjective Markov Decision Process…
Reinforcement learning in complex environments may require supervision to prevent the agent from attempting dangerous actions. As a result of supervisor intervention, the executed action may differ from the action specified by the policy.…
Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used in a way that wrongfully assumes that the state of an agent's environment does not change during action…
This paper presents a novel state representation for reward-free Markov decision processes. The idea is to learn, in a self-supervised manner, an embedding space where distances between pairs of embedded states correspond to the minimum…
Despite the tremendous success of Reinforcement Learning (RL) algorithms in simulation environments, applying RL to real-world applications still faces many challenges. A major concern is safety, in another word, constraint satisfaction.…
In reinforcement learning, different reward functions can be equivalent in terms of the optimal policies they induce. A particularly well-known and important example is potential shaping, a class of functions that can be added to any reward…
To perform robot manipulation tasks, a low-dimensional state of the environment typically needs to be estimated. However, designing a state estimator can sometimes be difficult, especially in environments with deformable objects. An…
Since the earliest days of reinforcement learning, the workhorse method for assigning credit to actions over time has been temporal-difference (TD) learning, which propagates credit backward timestep-by-timestep. This approach suffers when…