相关论文: Leveraging Prior Knowledge in Reinforcement Learni…
Learning from Demonstration is increasingly used for transferring operator manipulation skills to robots. In practice, it is important to cater for limited data and imperfect human demonstrations, as well as underlying safety constraints.…
Reward shaping is an effective technique for incorporating domain knowledge into reinforcement learning (RL). Existing approaches such as potential-based reward shaping normally make full use of a given shaping reward function. However,…
This paper discusses a system that accelerates reinforcement learning by using transfer from related tasks. Without such transfer, even if two tasks are very similar at some abstract level, an extensive re-learning effort is required. The…
Modern deep learning methods provide effective means to learn good representations. However, is a good representation itself sufficient for sample efficient reinforcement learning? This question has largely been studied only with respect to…
How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data? In this work we make a first contribution to answer this question in the context…
Reinforcement learning requires interaction with an environment, which is expensive for robots. This constraint necessitates approaches that work with limited environmental interaction by maximizing the reuse of previous experiences. We…
Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich…
Using function approximation to represent a value function is necessary for continuous and high-dimensional state spaces. Linear function approximation has desirable theoretical guarantees and often requires less compute and samples than…
Recommending a sequence of activities for an ongoing case requires that the recommendations conform to the underlying business process and meet the performance goal of either completion time or process outcome. Existing work on next…
We present an information-theoretic framework to learn fixed-dimensional embeddings for tasks in reinforcement learning. We leverage the idea that two tasks are similar if observing an agent's performance on one task reduces our uncertainty…
This work studies discrete-time discounted Markov decision processes with continuous state and action spaces and addresses the inverse problem of inferring a cost function from observed optimal behavior. We first consider the case in which…
Tasks where the set of possible actions depend discontinuously on the state pose a significant challenge for current reinforcement learning algorithms. For example, a locked door must be first unlocked, and then the handle turned before the…
Safety validation is important during the development of safety-critical autonomous systems but can require significant computational effort. Existing algorithms often start from scratch each time the system under test changes. We apply…
We develop the few-shot continual learning task from first principles and hypothesize an evolutionary motivation and mechanism of action for executive function as a contrastive value policy which resamples and relabels perception data via…
Policy gradient methods are appealing in deep reinforcement learning but suffer from high variance of gradient estimate. To reduce the variance, the state value function is applied commonly. However, the effect of the state value function…
Learning to solve sparse-reward reinforcement learning problems is difficult, due to the lack of guidance towards the goal. But in some problems, prior knowledge can be used to augment the learning process. Reward shaping is a way to…
Function approximation is widely used in reinforcement learning to handle the computational difficulties associated with very large state spaces. However, function approximation introduces errors which may lead to instabilities when using…
We investigate the fundamental problem of leveraging offline data to accelerate online reinforcement learning - a direction with strong potential but limited theoretical grounding. Our study centers on how to learn and apply value envelopes…
In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI). We consider the limitations of…
We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…