Related papers: Zero-Shot Context Generalization in Reinforcement …
We study the settings for which deep contextual embeddings (e.g., BERT) give large improvements in performance relative to classic pretrained embeddings (e.g., GloVe), and an even simpler baseline---random word embeddings---focusing on the…
We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to…
Achieving fast and stable off-policy learning in deep reinforcement learning (RL) is challenging. Most existing methods rely on semi-gradient temporal-difference (TD) methods for their simplicity and efficiency, but are consequently…
In order for autonomous mobile robots to navigate in human spaces, they must abide by our social norms. Reinforcement learning (RL) has emerged as an effective method to train sequential decision-making policies that are able to respect…
Document-level neural machine translation has yielded attractive improvements. However, majority of existing methods roughly use all context sentences in a fixed scope. They neglect the fact that different source sentences need different…
The deployment of machine learning models in safety-critical applications comes with the expectation that such models will perform well over a range of contexts (e.g., a vision model for classifying street signs should work in rural, city,…
Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability…
Cross-lingual word embeddings (CLWE) have been proven useful in many cross-lingual tasks. However, most existing approaches to learn CLWE including the ones with contextual embeddings are sense agnostic. In this work, we propose a novel…
Policy-based algorithms are among the most widely adopted techniques in model-free RL, thanks to their strong theoretical groundings and good properties in continuous action spaces. Unfortunately, these methods require precise and…
Shifting from traditional control strategies to Deep Reinforcement Learning (RL) for legged robots poses inherent challenges, especially when addressing real-world physical constraints during training. While high-fidelity simulations…
Reinforcement learning (RL) is empirically successful in complex nonlinear Markov decision processes (MDPs) with continuous state spaces. By contrast, the majority of theoretical RL literature requires the MDP to satisfy some form of linear…
Reinforcement learning (RL) is a classical tool to solve network control or policy optimization problems in unknown environments. The original Q-learning suffers from performance and complexity challenges across very large networks. Herein,…
Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have…
In recent years deep neural networks have been successfully applied to the domains of reinforcement learning \cite{bengio2009learning,krizhevsky2012imagenet,hinton2006reducing}. Deep reinforcement learning \cite{mnih2015human} is reported…
State-of-the-art meta reinforcement learning algorithms typically assume the setting of a single agent interacting with its environment in a sequential manner. A negative side-effect of this sequential execution paradigm is that, as the…
Fairness plays a crucial role in various multi-agent systems (e.g., communication networks, financial markets, etc.). Many multi-agent dynamical interactions can be cast as Markov Decision Processes (MDPs). While existing research has…
Bayesian reinforcement learning (BRL) is a method that merges principles from Bayesian statistics and reinforcement learning to make optimal decisions in uncertain environments. As a model-based RL method, it has two key components: (1)…
So far, expensive finetuning beyond the pretraining sequence length has been a requirement for effectively extending the context of language models (LM). In this work, we break this key bottleneck by Dropping the Positional Embeddings of…
Offline meta-reinforcement learning (meta-RL) methods, which adapt to unseen target tasks with prior experience, are essential in robot control tasks. Current methods typically utilize task contexts and skills as prior experience, where…
Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting…