Related papers: Learning Goal-Oriented Visual Dialog via Tempered …

In this paper, we present a deep reinforcement learning (RL) framework for iterative dialog policy optimization in end-to-end task-oriented dialog systems. Popular approaches in learning dialog policy with RL include letting a dialog agent…

In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback…

This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are considered:…

Effective persuasive dialogue agents adapt their strategies to individual users, accounting for the evolution of their psychological states and intentions throughout conversations. We present a personality-aware reinforcement learning…

Humans are able to identify a referred visual object in a complex scene via a few rounds of natural language communications. Success communication requires both parties to engage and learn to adapt for each other. In this paper, we…

Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards…

Reinforcement learning (RL) -- algorithms that teach artificial agents to interact with environments by maximising reward signals -- has achieved significant success in recent years. These successes have been facilitated by advances in…

Dialogue research tends to distinguish between chit-chat and goal-oriented tasks. While the former is arguably more naturalistic and has a wider use of language, the latter has clearer metrics and a straightforward learning signal. Humans…

Dialogue systems have attracted more and more attention. Recent advances on dialogue systems are overwhelmingly contributed by deep learning techniques, which have been employed to enhance a wide range of big data applications such as…

Large language models (LLMs) have emerged as powerful and general solutions to many natural language tasks. However, many of the most important applications of language generation are interactive, where an agent has to talk to a person to…

Reinforcement learning has emerged as a principled post-training paradigm for Temporal Video Grounding (TVG) due to its on-policy optimization, yet existing GRPO-based methods remain fundamentally constrained by sparse reward signals and…

Policy-gradient methods have received increased attention recently as a mechanism for learning to act in partially observable environments. They have shown promise for problems admitting memoryless policies but have been less successful…

We present the Generalized Policy Gradient (GPG) Theorem, specifically designed for Transformer-based policies. Notably, we demonstrate that both standard Policy Gradient Theorem and GRPO emerge as special cases within our GPG framework.…

Our ability to know when to trust the decisions made by machine learning systems has not kept up with the staggering improvements in their performance, limiting their applicability in high-stakes domains. We introduce Prover-Verifier Games…

This paper develops a policy learning method for tuning a pre-trained policy to adapt to additional tasks without altering the original task. A method named Adaptive Policy Gradient (APG) is proposed in this paper, which combines Bellman's…

Many problems at the intersection of combinatorics and computer science require solving for a permutation that optimally matches, ranks, or sorts some data. These problems usually have a task-specific, often non-differentiable objective…

Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters.…

Humans generally use natural language to communicate task requirements to each other. Ideally, natural language should also be usable for communicating goals to autonomous machines (e.g., robots) to minimize friction in task specification.…

A humanized dialogue system is expected to generate empathetic replies, which should be sensitive to the users' expressed emotion. The task of empathetic dialogue generation is proposed to address this problem. The essential challenges lie…

Recently advancements in deep learning allowed the development of end-to-end trained goal-oriented dialog systems. Although these systems already achieve good performance, some simplifications limit their usage in real-life scenarios. In…