Related papers: Guided Policy Search for Parameterized Skills usin…

We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following. To train LFMs, we obtain feedback from Large…

Training models to map natural language instructions to programs given target world supervision only requires searching for good programs at training time. Search is commonly done using beam search in the space of partial programs or…

We introduce a model-free algorithm for learning in Markov decision processes with parameterized actions-discrete actions with continuous parameters. At each step the agent must select both which action to use and which parameters to use…

This paper focuses on robotic reinforcement learning with sparse rewards for natural language goal representations. An open problem is the sample-inefficiency that stems from the compositionality of natural language, and from the grounding…

We consider the problem of finding a policy that maximizes an expected reward throughout the trajectory of an agent that interacts with an unknown environment. Frequently denoted Reinforcement Learning, this framework suffers from the need…

Accurately simulating the decisions of a specific individual remains challenging for large language models (LLMs), partly because persona information is often provided as static descriptions that miss the values, experiences, and contextual…

Language models are vulnerable to short adversarial suffixes that can reliably alter predictions. Previous works usually find such suffixes with gradient search or rule-based methods, but these are brittle and often tied to a single task or…

Modern AI systems such as self-driving cars and game-playing agents achieve superhuman performance, but often lack human-like generalization, interpretability, and inter-operability with human users. Inspired by the rich interactions…

Language-conditioned robotic skills make it possible to apply the high-level reasoning of Large Language Models (LLMs) to low-level robotic control. A remaining challenge is to acquire a diverse set of fundamental skills. Existing…

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former…

Recent progress in large language models (LLMs) has demonstrated the ability to learn and leverage Internet-scale knowledge through pre-training with autoregressive models. Unfortunately, applying such models to settings with embodied…

Automated fact-checking has been a challenging task for the research community. Prior work has explored various strategies, such as end-to-end training, retrieval-augmented generation, and prompt engineering, to build robust fact-checking…

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…

We introduce a large scale crowdsourced text adventure game as a research platform for studying grounded dialogue. In it, agents can perceive, emote, and act whilst conducting dialogue with other agents. Models and humans can both act as…

Many businesses and consumers are extending the capabilities of voice-based services such as Amazon Alexa, Google Home, Microsoft Cortana, and Apple Siri to create custom voice experiences (also known as skills). As the number of these…

Current endpointing (EP) solutions learn in a supervised framework, which does not allow the model to incorporate feedback and improve in an online setting. Also, it is a common practice to utilize costly grid-search to find the best…

Robots deployed in many real-world settings need to be able to acquire new skills and solve new tasks over time. Prior works on planning with skills often make assumptions on the structure of skills and tasks, such as subgoal skills, shared…

Active learning is able to significantly reduce the annotation cost for data-driven techniques. However, previous active learning approaches for natural language processing mainly depend on the entropy-based uncertainty criterion, and…

Syntax-guided synthesis is commonly used to generate programs encoding policies. In this approach, the set of programs, that can be written in a domain-specific language defines the search space, and an algorithm searches within this space…

Language models (LM) for interactive speech recognition systems are trained on large amounts of data and the model parameters are optimized on past user data. New application intents and interaction types are released for these systems over…