相关论文: ACE : Off-Policy Actor-Critic with Causality-Aware…

Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance it. However, RLVR training often suffers from policy…

When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, many environments…

Experiments are the gold standard for causal inference. In many applications, experimental units can often be recruited or chosen sequentially, and the adaptive execution of such experiments may offer greatly improved inference of causal…

This effort is focused on examining the behavior of reinforcement learning systems in personalization environments and detailing the differences in policy entropy associated with the type of learning algorithm utilized. We demonstrate that…

In this effort, we consider the impact of regularization on the diversity of actions taken by policies generated from reinforcement learning agents trained using a policy gradient. Policy gradient agents are prone to entropy collapse, which…

Tool-using agents based on Large Language Models (LLMs) excel in tasks such as mathematical reasoning and multi-hop question answering. However, in long trajectories, agents often trigger excessive and low-quality tool calls, increasing…

Reinforcement learning algorithms have had tremendous successes in online learning settings. However, these successes have relied on low-stakes interactions between the algorithmic agent and its environment. In many settings where RL could…

This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on…

We propose a data-driven framework to enable the modeling and optimization of human-machine interaction processes, e.g., systems aimed at assisting humans in decision-making or learning, work-load allocation, and interactive advertising.…

Recently, robust reinforcement learning (RL) methods designed to handle adversarial input observations have received significant attention, motivated by RL's inherent vulnerabilities. While existing approaches have demonstrated reasonable…

Estimating the unknown reward functions driving agents' behaviors is of central interest in inverse reinforcement learning and game theory. To tackle this problem, we develop a unified framework for reward function recovery in two-player…

Replaying data is a principal mechanism underlying the stability and data efficiency of off-policy reinforcement learning (RL). We present an effective yet simple framework to extend the use of replays across multiple experiments, minimally…

We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used in these algorithms. While these biases might work well for…

This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy. Such phenomenon is consistently observed across vast RL runs without entropy intervention, where the policy entropy…

The Collaborative Research Center for Everyday Activity Science & Engineering (CRC EASE) aims to enable robots to perform environmental interaction tasks with close to human capacity. It therefore employs a shared ontology to model the…

There are a variety of mechanisms (i.e., input types) for real-time human interaction that can facilitate effective human-robot teaming. For example, previous works have shown how teleoperation, corrective, and discrete (i.e., preference…

Policy-based reinforcement learning methods suffer from the policy collapse problem. We find valued-based reinforcement learning methods with {\epsilon}-greedy mechanism are capable of enjoying three characteristics, Closed-form Diversity,…

This paper investigates whether learning contingency-awareness and controllable aspects of an environment can lead to better exploration in reinforcement learning. To investigate this question, we consider an instantiation of this…

Maximum Causal Entropy (MCE) Inverse Optimal Control (IOC) has become an effective tool for modelling human behaviour in many control tasks. Its advantage over classic techniques for estimating human policies is the transferability of the…

Training LLM agents in multi-turn environments with sparse rewards, where completing a single task requires 30+ turns of interaction within an episode, presents a fundamental challenge for reinforcement learning. We identify a critical…