arXiv research

RH-UCRL combines pessimism and optimism for robust RL.

Proposes RFQI for robust RL using offline data.

Robust RL improves controller robustness to dynamics variations using adversarial populations.

New RL algorithm tackles online robust MDPs with uncertainty.

This thesis improves practical reinforcement learning methods with robustness, scalability, and efficiency.

RADIAL-RL improves deep RL agents' robustness against adversarial attacks.

Paper tackles robust offline RL for non-Markovian processes, improving efficiency and applicability.

New algorithms tackle robust RL with linear models, revealing unique challenges.

AdaRL improves robust RL by adaptively adjusting policy complexity.

We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on incorporating robustness into a state-of-the-art continuous control RL algorithm call…

Develops a framework for robust RL with dynamic risk measures.

RORL improves offline RL robustness with conservative smoothing.

This work bridges offline RL and DRL to address distributional shift.

New RL method tackles sim-to-real gap using interactive data collection.

New algorithm improves RL performance across different environments.

Robust RL with learned optimal adversary improves agent performance under adversarial state observations.

DR-RPO optimizes robust policies in RL with limited interaction, achieving sublinear regret.

This study tackles adversarial corruption in model-based reinforcement learning.

We introduce a sampling perspective to tackle the challenging task of training robust Reinforcement Learning (RL) agents. Leveraging the powerful Stochastic Gradient Langevin Dynamics, we present a novel, scalable two-player RL algorithm, which is a sampling variant of the two-player policy gradient method. Our algorit…

New methods tackle robust reinforcement learning in sparse, corrupted data.

Reinforcement learning (RL) constitutes a promising solution for alleviating the problem of traffic congestion. In particular, deep RL algorithms have been shown to produce adaptive traffic signal controllers that outperform conventional systems. However, in order to be reliable in highly dynamic urban areas, such cont…

Paper shows RLHF can be solved similarly to standard RL.

Paper introduces a new robust loss function for RL.

Paper studies S-rectangular DR-RL models for robust reinforcement learning with near-optimal sample complexity.

New model-free DR-RL algorithm with finite sample complexity.

Deep Reinforcement Learning (RL) demonstrates excellent performance on tasks that can be solved by trained policy. It plays a dominant role among cutting-edge machine learning approaches using multi-layer Neural networks (NNs). At the same time, Deep RL suffers from high sensitivity to noisy, incomplete, and misleading…

Paper tackles robust offline RL with heavy-tailed rewards.

RRPI improves offline RL by optimizing policies against worst-case dynamics.

Develops ODRPO to improve RL algorithms with better performance and stability.

MOOSE improves offline RL robustness by using dynamics models.

Paper tackles robust reinforcement learning with minimal data.

Off-policy reinforcement learning (RL) using a fixed offline dataset of logged interactions is an important consideration in real world applications. This paper studies offline RL using the DQN replay dataset comprising the entire replay experience of a DQN agent on 60 Atari 2600 games. We demonstrate that recent off-p…

This paper tackles RL issues with robust policies using historical data.

Improves reinforcement learning policies for robustness.

New framework improves sample efficiency and robustness in RL with smooth policies.

This work tackles robust RL in multi-agent settings, improving sample efficiency.

This paper analyzes risk-sensitive reinforcement learning with Conditional Value-at-Risk (CVaR) for robust Markov Decision Processes.

This review analyzes RL in finance, highlighting its advantages and challenges.

Enhances RL for jump processes using MSBVE algorithm.

This paper investigates the resilience and robustness of Deep Reinforcement Learning (DRL) policies to adversarial perturbations in the state space. We first present an approach for the disentanglement of vulnerabilities caused by representation learning of DRL agents from those that stem from the sensitivity of the DR…

RL applied to finance tasks, highlighting challenges and future directions.

Hybrid RL algorithm combines offline and online data for robust and efficient policy learning.

RePULSe improves language model alignment by reducing undesired outputs without sacrificing overall performance.

Study uses RL to hedge financial derivatives, showing robust strategies outperform non-robust ones.

The dichotomous coordinate descent (DCD) algorithm has been successfully used for significant reduction in the complexity of recursive least squares (RLS) algorithms. In this work, we generalize the application of the DCD algorithm to RLS adaptive filtering in impulsive noise scenarios and derive a unified update formu…

RPI combines imitation and reinforcement learning to improve policies efficiently.

Experimentally, it has been observed that humans and animals often make decisions that do not maximize their expected utility, but rather choose outcomes randomly, with probability proportional to expected utility. Probability matching, as this strategy is called, is equivalent to maximum entropy reinforcement learning…

Paper combines RL with classifiers to improve financial trading strategies.