Recent studies have demonstrated the potential to control paraphrase generation, such as through syntax, which has broad applications in various downstream tasks. However, these methods often require detailed parse trees or syntactic exemplars, countering human-like paraphrasing behavior in language use. Furthermore, an inference gap exists, as control specifications are only available during training but not during inference. In this work, we propose a new setup for controlled paraphrase generation. Specifically, we represent user intent as action tokens, embedding and concatenating them with text embeddings, thus flowing together into a self-attention encoder for representation fusion. To address the inference gap, we introduce an optional action token as a placeholder that encourages the model to determine the appropriate action independently when users' intended actions are not provided. Experimental results show that our method successfully enables precise action-controlled paraphrasing and preserves or even enhances performance compared to conventional uncontrolled methods when actions are not given. Our findings promote the concept of action-controlled paraphrasing for a more user-centered design.

In this paper we present a computational modeling account of an active self in artificial agents. In particular we focus on how an agent can be equipped with a sense of control and how it arises in autonomous situated action and, in turn, influences action control. We argue that this requires laying out an embodied cognitive model that combines bottom-up processes (sensorimotor learning and fine-grained adaptation of control) with top-down processes (cognitive processes for strategy selection and decision-making). We present such a conceptual computational architecture based on principles of predictive processing and free energy minimization. Using this general model, we describe how a sense of control can form across the levels of a control hierarchy and how this can support action control in an unpredictable environment. We present an implementation of this model as well as first evaluations in a simulated task scenario, in which an autonomous agent has to cope with un-/predictable situations and experiences corresponding sense of control. We explore different model parameter settings that lead to different ways of combining low-level and high-level action control. The results show the importance of appropriately weighting information in situations where the need for low/high-level action control varies and they demonstrate how the sense of control can facilitate this.

We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games. This problem involves far more complicated state and action spaces than those of traditional 1v1 games, such as Go and Atari series, which makes it very difficult to search any policies with human-level performance. In this paper, we present a deep reinforcement learning framework to tackle this problem from the perspectives of both system and algorithm. Our system is of low coupling and high scalability, which enables efficient explorations at large scale. Our algorithm includes several novel strategies, including control dependency decoupling, action mask, target attention, and dual-clip PPO, with which our proposed actor-critic network can be effectively trained in our system. Tested on the MOBA game Honor of Kings, the trained AI agents can defeat top professional human players in full 1v1 games. Introduction Deep reinforcement learning (DRL) has been widely used for building agents to learn complex control in competitive environments. In the competitive setting, a considerable amount of existing DRL research adopt two-agent games as the testbed, i.e., one agent versus another (1v1). Among them, Atari series and board games have been widely studied. For example, a human-level agent for playing Atari games is trained with deep Q-networks (Mnih et al. 2015). The incorporation of supervised learning and self-play into the training brings the agent to the level of beating human professionals in the game of Go (Silver et al. 2016).