Related papers: Pre-training of Deep RL Agents for Improved Learni…
Recent advances in Reinforcement Learning (RL) have surpassed human-level performance in many simulated environments. However, existing reinforcement learning techniques are incapable of explicitly incorporating already known…
Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori. We show how a policy can be…
In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A…
Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from…
Computers can understand and then engage with people in an emotionally intelligent way thanks to speech-emotion recognition (SER). However, the performance of SER in cross-corpus and real-world live data feed scenarios can be significantly…
In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-designed optimizers. Reinforcement learning (RL) is…
The main challenge in learning image-conditioned robotic policies is acquiring a visual representation conducive to low-level control. Due to the high dimensionality of the image space, learning a good visual representation requires a…
This paper proposes a detailed and extensive comparison of the Trust Region Policy Optimization and DeepQ-Network with Normalized Advantage Functions with respect to other state of the art algorithms, namely Deep Deterministic Policy…
Reinforcement learning (RL) algorithms hold the promise of enabling autonomous skill acquisition for robotic systems. However, in practice, real-world robotic RL typically requires time consuming data collection and frequent human…
We introduce a new representation learning algorithm suited to the context of domain adaptation, in which data at training and test time come from similar but different distributions. Our algorithm is directly inspired by theory on domain…
Accurate state estimation is a fundamental component of robotic control. In robotic manipulation tasks, as is our focus in this work, state estimation is essential for identifying the positions of objects in the scene, forming the basis of…
Key challenges for the deployment of reinforcement learning (RL) agents in the real world are the discovery, representation and reuse of skills in the absence of a reward function. To this end, we propose a novel approach to learn a…
In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, generalization across different environments is known to be hard.…
Images seen during test time are often not from the same distribution as images used for learning. This problem, known as domain shift, occurs when training classifiers from object-centric internet image databases and trying to apply them…
State-of-the-art reinforcement learning algorithms predominantly learn a policy from either a numerical state vector or images. Both approaches generally do not take structural knowledge of the task into account, which is especially…
We present a machine learning framework for multi-agent systems to learn both the optimal policy for maximizing the rewards and the encoding of the high dimensional visual observation. The encoding is useful for sharing local visual…
Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks. However, in the reinforcement learning domain, multi-task learning has not…
There has been an increasing interest in 3D indoor navigation, where a robot in an environment moves to a target according to an instruction. To deploy a robot for navigation in the physical world, lots of training data is required to learn…
Sim-to-real transfer is a fundamental challenge in robot reinforcement learning. Discrepancies between simulation and reality can significantly impair policy performance, especially if it receives high-dimensional inputs such as dense depth…
In this paper we investigate the properties of representations learned by deep reinforcement learning systems. Much of the early work on representations for reinforcement learning focused on designing fixed-basis architectures to achieve…