Related papers: Regularized Soft Actor-Critic for Behavior Transfe…

We study controllable text summarization which allows users to gain control on a particular attribute (e.g., length limit) of the generated summaries. In this work, we propose a novel training framework based on Constrained Markov Decision…

We consider a multi-agent reinforcement learning problem where each agent seeks to maximize a shared reward while interacting with other agents, and they may or may not be able to communicate. Typically the agents do not have access to…

Imitation Learning from observation describes policy learning in a similar way to human learning. An agent's policy is trained by observing an expert performing a task. While many state-only imitation learning approaches are based on…

Human-computer interactive systems that rely on machine learning are becoming paramount to the lives of millions of people who use digital assistants on a daily basis. Yet, further advances are limited by the availability of data and the…

Actor-critic methods, a type of model-free Reinforcement Learning, have been successfully applied to challenging tasks in continuous control, often achieving state-of-the art performance. However, wide-scale adoption of these methods in…

We present Distributional Soft Actor-Critic (DSAC), a distributional reinforcement learning (RL) algorithm that combines the strengths of distributional information of accumulated rewards and entropy-driven exploration from Soft…

In supervised learning, we fit a single statistical model to a given data set, assuming that the data is associated with a singular task, which yields well-tuned models for specific use, but does not adapt well to new contexts. By contrast,…

Complex behaviors are often driven by an internal model, which integrates sensory information over time and facilitates long-term planning. Inferring an agent's internal model is a crucial ingredient in social interactions (theory of mind),…

This paper addresses the problem of training a reinforcement learning (RL) policy under partial observability by exploiting a privileged, anytime-feasible planner agent available exclusively during training. We formalize this as a Partially…

Reinforcement learning (RL) has achieved remarkable performance in numerous sequential decision making and control tasks. However, a common problem is that learned nearly optimal policy always overfits to the training environment and may…

Blame attribution is one of the key aspects of accountable decision making, as it provides means to quantify the responsibility of an agent for a decision making outcome. In this paper, we study blame attribution in the context of…

Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes…

Imitation learning seeks to circumvent the difficulty in designing proper reward functions for training agents by utilizing expert behavior. With environments modeled as Markov Decision Processes (MDP), most of the existing imitation…

The sense of touch, being the earliest sensory system to develop in a human body [1], plays a critical part of our daily interaction with the environment. In order to successfully complete a task, many manipulation interactions require…

Risk-bounded motion planning is an important yet difficult problem for safety-critical tasks. While existing mathematical programming methods offer theoretical guarantees in the context of constrained Markov decision processes, they either…

Fine-grained simulation of floor construction processes is essential for supporting lean management and the integration of information technology. However, existing research does not adequately address the on-site decision-making of…

We study the robustness of deep reinforcement learning algorithms against distribution shifts within contextual multi-stage stochastic combinatorial optimization problems from the operations research domain. In this context, risk-sensitive…

Most prior approaches to offline reinforcement learning (RL) utilize \textit{behavior regularization}, typically augmenting existing off-policy actor critic algorithms with a penalty measuring divergence between the policy and the offline…

A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In…

Mutual adaptation is a central challenge in human--AI teaming, as humans naturally adjust their strategies in response to a robot's policy. Existing approaches aim to improve diversity in training partners to approximate human behavior, but…