Deep Reinforcement Learning (DRL) is widely used in task-oriented dialogue systems to optimize dialogue policy, but it struggles to balance exploration and exploitation due to the high dimensionality of state and action spaces. This challenge often results in local optima or poor convergence. Evolutionary Algorithms (EAs) have been proven to effectively explore the solution space of neural networks by maintaining population diversity. Inspired by this, we innovatively combine the global search capabilities of EA with the local optimization of DRL to achieve a balance between exploration and exploitation. Nevertheless, the inherent flexibility of natural language in dialogue tasks complicates this direct integration, leading to prolonged evolutionary times. Thus, we further propose an elite individual injection mechanism to enhance EA’s search efficiency by adaptively introducing best-performing individuals into the population. Experiments across four datasets show that our approach significantly improves the balance between exploration and exploitation, boosting performance. Moreover, the effectiveness of the EII mechanism in reducing exploration time has been demonstrated, achieving an efficient integration of EA and DRL on task-oriented dialogue policy tasks.

Dialogue policy trains an agent to select dialogue actions frequently implemented via deep reinforcement learning (DRL). The model-based reinforcement methods built a world model to generate simulated data to alleviate the sample inefficiency. However, traditional world model methods merely consider one-step dialogues, leading to an inaccurate environmental simulation. Furthermore, different users may have different intention preferences, while most existing studies lack consideration of the intention-preferences causal relationship. This paper proposes a novel framework for dialogue policy learning named MCA, implemented through model-based reinforcement learning with automatically constructed causal chains. The MCA model utilizes an autoregressive Transformer to model dialogue trajectories, enabling a more accurate simulation of the environment. Additionally, it constructs a causal chains module that outputs latent preference distributions for intention-action pairs, thereby elucidating the relationship between user intentions and agent actions. The experimental results show that MCA can achieve state-of-the-art performances on three dialogue datasets over the compared dialogue agents, highlighting its effectiveness and robustness.

The flexibility of natural language significantly expands the action space in task-oriented dialogue systems, causing inefficient exploration and slow convergence in deep reinforcement learning (DRL)-based policy optimization. Pre-trained large language models (LLMs), with world knowledge and semantic understanding, offer promising solutions. To this end, we propose LLM-Guided DRL via Semantic-Aware Action Pruning (LLMSAP), a novel framework that synergizes pretrained LLMs with DRL. LLMSAP leverages the world knowledge and contextual understanding of LLMs to guide decision-making via an action feasibility assessment. Instead of requiring LLMs to directly generate optimal actions due to their limited precision in sequential decision tasks, LLMSAP employs a lightweight action pruning mechanism. Specifically, LLMs act as action filters, rapidly eliminating semantically implausible or low-potential actions from multi-turn dialogue context, allowing the DRL agent to focus exploration on a refined candidate subset. This two-stage framework (“prune-then-optimize”) avoids extensive LLM fine-tuning while preserving the decision-making precision of DRL. Experiments on multiple benchmarks verify the effectiveness of LLMSAP.

Reinforcement learning shows promise in optimizing dialogue policies, but addressing the challenge of reward sparsity remains crucial. While curriculum learning offers a practical solution by strategically training policies from simple to complex, it hinges on the assumption of a gradual increase in goal difficulty to ensure a smooth knowledge transition across varied complexities. In complex dialogue environments without intermediate goals, achieving seamless knowledge transitions becomes tricky. This paper proposes a novel Bootstrapped Policy Learning (BPL) framework, which adaptively tailors progressively challenging subgoal curriculum for each complex goal through goal shaping, ensuring a smooth knowledge transition. Goal shaping involves goal decomposition and evolution, decomposing complex goals into subgoals with solvable maximum difficulty and progressively increasing difficulty as the policy improves. Moreover, to enhance BPL’s adaptability across various environments, we explore various combinations of goal decomposition and evolution within BPL, and identify two universal curriculum patterns that remain effective across different dialogue environments, independent of specific environmental constraints. By integrating the summarized curriculum patterns, our BPL has exhibited efficacy and versatility across four publicly available datasets with different difficulty levels.

Training a task-oriented dialogue policy using deep reinforcement learning is promising but requires extensive environment exploration. The amount of wasted invalid exploration makes policy learning inefficient. In this paper, we define and argue that dead-end states are important reasons for invalid exploration. When a conversation enters a dead-end state, regardless of the actions taken afterward, it will continue in a dead-end trajectory until the agent reaches a termination state or maximum turn. We propose a Dead-end Detection and Resurrection (DDR) method that detects dead-end states in an efficient manner and provides a rescue action to guide and correct the exploration direction. To prevent dialogue policies from repeating errors, DDR also performs dialogue data augmentation by adding relevant experiences that include dead-end states and penalties into the experience pool. We first validate the dead-end detection reliability and then demonstrate the effectiveness and generality of the method across various domains through experiments on four public dialogue datasets.

Deep reinforcement learning has shown great potential in training dialogue policies. However, its favorable performance comes at the cost of many rounds of interaction. Most of the existing dialogue policy methods rely on a single learning system, while the human brain has two specialized learning and memory systems, supporting to find good solutions without requiring copious examples. Inspired by the human brain, this paper proposes a novel complementary policy learning (CPL) framework, which exploits the complementary advantages of the episodic memory (EM) policy and the deep Q-network (DQN) policy to achieve fast and effective dialogue policy learning. In order to coordinate between the two policies, we proposed a confidence controller to control the complementary time according to their relative efficacy at different stages. Furthermore, memory connectivity and time pruning are proposed to guarantee the flexible and adaptive generalization of the EM policy in dialog tasks. Experimental results on three dialogue datasets show that our method significantly outperforms existing methods relying on a single learning system.