Recently, reward-conditioned reinforcement learning (RCRL) has gained popularity due to its simplicity, flexibility, and off-policy nature.
In this work, we propose Symmetrical Prompt Enhancement (SPE), a continuous prompt-based method for factual probing in PLMs that leverages the symmetry of the task by constructing symmetrical prompts for subject and object prediction.
Effectively exploring the environment is a key challenge in reinforcement learning (RL).
Controllable and realistic traffic simulation is critical for developing and verifying autonomous vehicles.
Humans are remarkably good at understanding and reasoning about complex visual scenes.
Autoregressive generative models are commonly used, especially for those tasks involving sequential data.
It is motivated by an empirical finding that transformer-based models trained with empirical risk minimization (ERM) outperform CNN-based models employing state-of-the-art (SOTA) DG algorithms on multiple DG datasets.
Ranked #9 on Domain Generalization on DomainNet (using extra training data)
One of the greatest challenges of reinforcement learning is efficient exploration, especially when training signals are sparse or deceptive.
This paper targets on learning-based novel view synthesis from a single or limited 2D images without the pose supervision.
In this paper, in order to devise robust DA algorithms, we first systematically analyze the limitations of DM based methods, and then build new benchmarks with more realistic domain shifts to evaluate the well-accepted DM methods.
To make that practical, we show that sampling from this modified density can be achieved by sampling in latent space according to an energy-based model induced by the sum of the latent prior log-density and the discriminator output score.
We test the verifier network on out-of-distribution detection and adversarial example detection problems, as well as anomaly detection problems in structured prediction tasks such as image caption generation.
We propose to incorporate inter-class correlations in a Wasserstein training framework by pre-defining ($i. e.,$ using arc length of a circle) or adaptively learning the ground metric.
In this paper, we propose a conceptually simple and general framework called MetaGAN for few-shot learning problems.
Model-free deep reinforcement learning algorithms are able to successfully solve a wide range of continuous control tasks, but typically require many on-policy samples to achieve good performance.
In general, a Resnet block tends to concentrate representation learning behavior in the first few layers while higher layers perform iterative refinement of features.
We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator.
Despite the successes in capturing continuous distributions, the application of generative adversarial networks (GANs) to discrete settings, like natural language tasks, is rather restricted.
Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes.
In this paper, we systematically analyze the connecting architectures of recurrent neural networks (RNNs).
Ranked #22 on Language Modelling on Text8