Search Results for author:
Found 26 papers, 6 papers with code
Neuro-Symbolic Approaches for Text-Based Policy Learning
We outline a method for end-to-end differentiable symbolic rule learning and show that such symbolic policies outperform previous state-of-the-art methods in text-based RL for the coin collector environment from 5-10x fewer training games.
Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency
We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a scalable, semi-supervised method for training a neural semantic parser.
Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing
Nearly all general-purpose neural semantic parsers generate logical forms in a strictly top-down autoregressive fashion.
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach
Machine learning problems with multiple objective functions appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance metrics such as fairness, safety and accuracy; or, in multi-task learning where multiple tasks are optimized jointly, sharing inductive bias between them.
Neuro-Symbolic Reinforcement Learning with First-Order Logic
Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided.
LOA: Logical Optimal Actions for Text-based Interaction Games
We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural network and symbolic knowledge acquisition approach for natural language interaction games.
Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents
This improves the agent's overall understanding of the game 'scene' and objects' relationships to the world around them, and the variety of visual representations on offer allow the agent to generate a better generalization of a relationship.
Reinforcement Learning with External Knowledge by using Logical Neural Networks
Specifically, we propose an integrated method that enables model-free reinforcement learning from external knowledge sources in an LNNs-based logical constrained framework such as action shielding and guide.
Image inpainting using frequency domain priors
To alleviate these problems, we investigate if it is possible to obtain better performance by training the networks using frequency domain information (Discrete Fourier Transform) along with the spatial domain information.
VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning
The goal is to force an RL agent to use both text and visual features to predict natural language action commands for solving the final task of cooking a meal.
Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games
Our bootstrapped agent shows improved generalization in solving unseen TextWorld games, using 10x-20x fewer training games compared to previous state-of-the-art methods despite requiring less number of training episodes.
Investigating Generalization in Neural Networks under Optimally Evolved Training Perturbations
In this paper, we study the generalization properties of neural networks under input perturbations and show that minimal training data corruption by a few pixel modifications can cause drastic overfitting.
Unsupervised Temporal Feature Aggregation for Event Detection in Unstructured Sports Videos
In this paper, we study the case of event detection in sports videos for unstructured environments with arbitrary camera angles.
Assessing Robustness of Deep learning Methods in Dermatological Workflow
This paper aims to evaluate the suitability of current deep learning methods for clinical workflow especially by focusing on dermatology.
Lunar surface image restoration using U-net based deep neural networks
Image restoration is a technique that reconstructs a feasible estimate of the original image from the noisy observation.
Injective State-Image Mapping facilitates Visual Adversarial Imitation Learning
Experimental results show that the proposed adversarial learning method from raw videos produces a similar performance to state-of-the-art imitation learning techniques while frequently outperforming existing hand-crafted video imitation methods.
Constrained Exploration and Recovery from Experience Shaping
We consider the problem of reinforcement learning under safety requirements, in which an agent is trained to complete a given task, typically formalized as the maximization of a reward signal over time, while concurrently avoiding undesirable actions or states, associated to lower rewards, or penalties.
Transfer Learning From Synthetic To Real Images Using Variational Autoencoders For Precise Position Detection
Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data.
Focusing on What is Relevant: Time-Series Learning and Understanding using Attention
This paper is a contribution towards interpretability of the deep learning models in different applications of time-series.
Internal Model from Observations for Reward Shaping
During reinforcement learning, the agent predicts the reward as a function of the difference between the actual state and the state predicted by the internal model.
Reward Estimation via State Prediction
We present a novel reward estimation method that is based on a finite sample of optimal state trajectories from expert demon- strations and can be used for guiding an agent to mimic the expert behavior.
Model-based imitation learning from state trajectories
We present a model-based imitation learning method that can learn environment-specific optimal actions only from expert state trajectories.
Transfer learning from synthetic to real images using variational autoencoders for robotic applications
It detects object positions 6 to 7 times more precisely than the baseline of directly learning from the dataset of the real images.
Conditional generation of multi-modal data using constrained embedding space mapping
We present a conditional generative model that maps low-dimensional embeddings of multiple modalities of data to a common latent space hence extracting semantic relationships between them.
Can fully convolutional networks perform well for general image restoration problems?
We propose a fully convolutional model, that learns a direct end-to-end mapping between the corrupted images as input and the desired clean images as output.
