Related papers: DRED: Zero-Shot Transfer in Reinforcement Learning…
The wider application of end-to-end learning methods to embodied decision-making domains remains bottlenecked by their reliance on a superabundance of training data representative of the target domain. Meta-reinforcement learning (meta-RL)…
Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the completion of some goal. Goal-directed RL has seen large gains in…
Deep reinforcement learning (RL) agents often fail to generalize to unseen scenarios, even when they are trained on many instances of semantically similar environments. Data augmentation has recently been shown to improve the sample…
This paper studies the problem of autonomous exploration under localization uncertainty for a mobile robot with 3D range sensing. We present a framework for self-learning a high-performance exploration policy in a single simulation…
Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that…
Domain Randomization (DR) is known to require a significant amount of training data for good performance. We argue that this is due to DR's strategy of random data generation using a uniform distribution over simulation parameters, as a…
Agents trained with deep reinforcement learning algorithms are capable of performing highly complex tasks including locomotion in continuous environments. We investigate transferring the learning acquired in one task to a set of previously…
The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here, we consider tests of out-of-sample generalisation that…
Although deep reinforcement learning (deep RL) methods have lots of strengths that are favorable if applied to autonomous driving, real deep RL applications in autonomous driving have been slowed down by the modeling gap between the source…
Deep reinforcement learning (RL) agents often fail to generalize to unseen environments (yet semantically similar to trained agents), particularly when they are trained on high-dimensional state spaces, such as images. In this paper, we…
Modern reinforcement learning (RL) systems capture deep truths about general, human problem-solving. In domains where new data can be simulated cheaply, these systems uncover sequential decision-making policies that far exceed the ability…
In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks. This work relates to meta…
Reinforcement Learning (RL) agents are often unable to generalise well to environment variations in the state space that were not observed during training. This issue is especially problematic for image-based RL, where a change in just one…
Reinforcement learning (RL) in non-stationary environments is challenging, as changing dynamics and rewards quickly make past experiences outdated. Traditional experience replay (ER) methods, especially those using TD-error prioritization,…
Deep reinforcement learning (DRL) has shown remarkable success in simulation domains, yet its application in designing robot controllers remains limited, due to its single-task orientation and insufficient adaptability to environmental…
Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolutionary framework in which a teacher adaptively generates…
The sample efficiency challenge in Deep Reinforcement Learning (DRL) compromises its industrial adoption due to the high cost and time demands of real-world training. Virtual environments offer a cost-effective alternative for training DRL…
Many real-world problems are compositional - solving them requires completing interdependent sub-tasks, either in series or in parallel, that can be represented as a dependency graph. Deep reinforcement learning (RL) agents often struggle…
Deep generative models (DGMs) are data-eager because learning a complex model on limited data suffers from a large variance and easily overfits. Inspired by the classical perspective of the bias-variance tradeoff, we propose regularized…
Zero-shot learning methods typically assume that the new, unseen classes encountered during deployment come from the same distribution as the the classes in the training set. However, real-world scenarios often involve class distribution…