Search Results for author:
Found 23 papers, 15 papers with code
Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control
This paper proposes a general method for improving the structure and quality of sequences generated by a recurrent neural network (RNN), while maintaining information originally learned from data, as well as sample diversity.
Multimodal Autoencoder: A Deep Learning Approach to Filling In Missing Sensor Data and Enabling Better Mood Prediction
To accomplish forecasting of mood in real-world situations, affective computing systems need to collect and learn from multimodal data collected over weeks or months of daily use.
Learning via social awareness: Improving a deep generative sketching model with facial feedback
We use a Latent Constraints GAN (LC-GAN) to learn from the facial feedback of a small group of viewers, by optimizing the model to produce sketches that it predicts will lead to more positive facial expressions.
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
We propose a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning (MARL), through rewarding agents for having causal influence over other agents' actions.
Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
Therefore, we also employ influence to train agents to use an explicit communication channel, and find that it leads to more effective communication and higher collective reward.
Tackling Climate Change with Machine Learning
Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help.
Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
To investigate the strengths of this novel metric and interactive evaluation in comparison to state-of-the-art metrics and human evaluation of static conversations, we perform extended experiments with a set of models, including several that make novel improvements to recent hierarchical dialog generation architectures through sentiment and semantic knowledge distillation on the utterance level.
Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment.
Hierarchical Reinforcement Learning for Open-Domain Dialog
Open-domain dialog generation is a challenging problem; maximum likelihood training can lead to repetitive outputs, models have difficulty tracking long-term conversational goals, and training on standard movie or online datasets may lead to the generation of inappropriate, biased, or offensive text.
Way Off-Policy Batch Deep Reinforcement Learning of Human Preferences in Dialog
This is a critical shortcoming for applying RL to real-world problems where collecting data is expensive, and models must be tested offline before being deployed to interact with the environment -- e. g. systems that learn from human interaction.
Emergent Social Learning via Multi-agent Reinforcement Learning
We analyze the reasons for this deficiency, and show that by imposing constraints on the training environment and introducing a model-based auxiliary loss we are able to obtain generalized social learning policies which enable agents to: i) discover complex skills that are not learned from single-agent training, and ii) adapt online to novel environments by taking cues from experts present in the new environment.
Human-centric Dialog Training via Offline Reinforcement Learning
We start by hosting models online, and gather human feedback from real-time, open-ended conversations, which we then use to train and improve the models using offline reinforcement learning (RL).
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design
We call our technique Protagonist Antagonist Induced Regret Environment Design (PAIRED).
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
This allows us to disentangle shared features and dynamics of the environment from agent-specific rewards and policies.
Adversarial Environment Generation for Learning to Navigate the Web
The regret objective trains the adversary to design a curriculum of environments that are "just-the-right-challenge" for the navigator agents; our results show that over time, the adversary learns to generate increasingly complex web navigation tasks.
Joint Attention for Multi-Agent Coordination and Social Learning
We then train agents to minimize the difference between the attention weights that they apply to the environment at each timestep, and the attention of other agents.
Explore and Control with Adversarial Surprise
Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering.
Less is More: Generating Grounded Navigation Instructions from Landmarks
We study the automatic generation of navigation instructions from 360-degree images captured on indoor routes.
Environment Generation for Zero-Shot Compositional Reinforcement Learning
We learn to generate environments composed of multiple pages or rooms, and train RL agents capable of completing wide-range of complex tasks in those environments.
Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience
IRL can provide a generalizable and compact representation for apprenticeship learning, and enable accurately inferring the preferences of a human in order to assist them.
Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration
It is unclear how scalable single-agent formulations are as we increase the complexity of the design space (e. g., full stack System-on-Chip design).
Impossibility Theorems for Feature Attribution
Despite a sea of interpretability methods that can produce plausible explanations, the field has also empirically seen many failure cases of such methods.
Moral Foundations of Large Language Models
Finally, we show that we can adversarially select prompts that encourage the moral to exhibit a particular set of moral foundations, and that this can affect the model's behavior on downstream tasks.
