相关论文: Learning Task Specifications from Demonstrations

In the last decade, Deep Reinforcement Learning has evolved into a powerful tool for complex sequential decision-making problems. It combines deep learning's proficiency in processing rich input signals with reinforcement learning's…

In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming can range from simple behaviors like sycophancy to…

Parameter estimation in Markov random fields (MRFs) is a difficult task, in which inference over the network is run in the inner loop of a gradient descent procedure. Replacing exact inference with approximate methods such as loopy belief…

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

A misspecified reward can degrade sample efficiency and induce undesired behaviors in reinforcement learning (RL) problems. We propose symbolic reward machines for incorporating high-level task knowledge when specifying the reward signals.…

In this paper, we consider the problem of recovering time-varying reward functions from either optimal policies or demonstrations coming from a max entropy reinforcement learning problem. This problem is highly ill-posed without additional…

Learning from demonstration is an effective method for human users to instruct desired robot behaviour. However, for most non-trivial tasks of practical interest, efficient learning from demonstration depends crucially on inductive bias in…

Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle,…

Bayesian inverse reinforcement learning (IRL) methods are ideal for safe imitation learning, as they allow a learning agent to reason about reward uncertainty and the safety of a learned policy. However, Bayesian IRL is computationally…

When solving long-horizon tasks, it is intriguing to decompose the high-level task into subtasks. Decomposing experiences into reusable subtasks can improve data efficiency, accelerate policy generalization, and in general provide promising…

A central problem in business concerns the optimal allocation of limited resources to a set of available tasks, where the payoff of these tasks is inherently uncertain. In credit card fraud detection, for instance, a bank can only assign a…

Informative path-planning is a well established approach to visual-servoing and active viewpoint selection in robotics, but typically assumes that a suitable cost function or goal state is known. This work considers the inverse problem,…

Learning auxiliary tasks, such as multiple predictions about the world, can provide many benefits to reinforcement learning systems. A variety of off-policy learning algorithms have been developed to learn such predictions, but as yet there…

The goal of learning from demonstrations is to learn a policy for an agent (imitator) by mimicking the behavior in the demonstrations. Prior works on learning from demonstrations assume that the demonstrations are collected by a…

In-Context Learning (ICL) is an emergent capability of Large Language Models (LLMs). Only a few demonstrations enable LLMs to be used as blackbox for new tasks. Previous studies have shown that using LLMs' outputs as labels is effective in…

Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned with a subset of the dataset are thus uncertain and the…

State-of-the-art NLP methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors,…

By allowing models to predict without task-specific training, in-context learning (ICL) with pretrained LLMs has enormous potential in NLP. However, a number of problems persist in ICL. In particular, its performance is sensitive to the…

We propose a framework for verifiable and compositional reinforcement learning (RL) in which a collection of RL subsystems, each of which learns to accomplish a separate subtask, are composed to achieve an overall task. The framework…

Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functions as well as large variances in the learning signals. We…