Related papers: Proximal Policy Optimization for Improved Converge…

We present a novel method and analysis to train generative adversarial networks (GAN) in a stable manner. As shown in recent analysis, training is often undermined by the probability distribution of the data being zero on neighborhoods of…

Conditional generative adversarial networks (cGANs) have demonstrated remarkable success due to their class-wise controllability and superior quality for complex generation tasks. Typical cGANs solve the joint distribution matching problem…

Despite large incentives, ecorrectness in software remains an elusive goal. Declarative programming techniques, where algorithms are derived from a specification of the desired behavior, offer hope to address this problem, since there is a…

Despite the successes in capturing continuous distributions, the application of generative adversarial networks (GANs) to discrete settings, like natural language tasks, is rather restricted. The fundamental reason is the difficulty of…

Most of the existing generative adversarial networks (GAN) for text generation suffer from the instability of reinforcement learning training algorithms such as policy gradient, leading to unstable performance. To tackle this problem, we…

We propose a novel training procedure for improving the performance of generative adversarial networks (GANs), especially to bidirectional GANs. First, we enforce that the empirical distribution of the inverse inference network matches the…

Retrieval-Augmented Generation (RAG) systems traditionally treat retrieval and generation as separate processes, requiring explicit textual queries to connect them. This separation can limit the ability of models to generalize across…

The task of infomin learning aims to learn a representation with high utility while being uninformative about a specified target, with the latter achieved by minimising the mutual information between the representation and the target. It…

Training of Generative Adversarial Networks (GANs) is notoriously fragile, requiring to maintain a careful balance between the generator and the discriminator in order to perform well. To mitigate this issue we introduce a new…

We present a simple and intuitive approach for interactive control of physically simulated characters. Our work builds upon generative adversarial networks (GAN) and reinforcement learning, and introduces an imitation learning framework…

Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially for text generation. To solve this issue, we propose a new…

Retrieval-augmented generation (RAG) has become a fundamental paradigm for addressing the challenges faced by large language models in handling real-time information and domain-specific problems. Traditional RAG systems primarily rely on…

Generative adversarial networks (GANs) are successful deep generative models. GANs are based on a two-player minimax game. However, the objective function derived in the original motivation is changed to obtain stronger gradients when…

We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.…

Inverse reinforcement learning (IRL) addresses the problem of recovering a task description given a demonstration of the optimal policy used to solve such a task. The optimal policy is usually provided by an expert or teacher, making IRL…

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…

Score function-based natural language generation (NLG) approaches such as REINFORCE, in general, suffer from low sample efficiency and training instability problems. This is mainly due to the non-differentiable nature of the discrete space…

This paper presents a new conditional GAN (named convex relaxing CGAN or crCGAN) to replicate the conventional constrained topology optimization algorithms in an extremely effective and efficient process. The proposed crCGAN consists of a…

Understanding an agent's goals from its behavior is fundamental to aligning AI systems with human intentions. Existing goal recognition methods typically rely on an optimal goal-oriented policy representation, which may differ from the…

This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that…