Related papers: Dynamics-aware Embeddings
The reinforcement learning algorithms that focus on how to compute the gradient and choose next actions, are effectively improved the performance of the agents. However, these algorithms are environment-agnostic. This means that the…
Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on…
Many real-world applications require an agent to make robust and deliberate decisions with multimodal information (e.g., robots with multi-sensory inputs). However, it is very challenging to train the agent via reinforcement learning (RL)…
Recent unsupervised pre-training methods have shown to be effective on language and vision domains by learning useful representations for multiple downstream tasks. In this paper, we investigate if such unsupervised pre-training methods can…
Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples since they learn from scratch. Meta-RL aims to address this challenge by leveraging experience…
A major challenge in reinforcement learning (RL) is the design of agents that are able to generalize across tasks that share common dynamics. A viable solution is meta-reinforcement learning, which identifies common structures among past…
Learned models of the environment provide reinforcement learning (RL) agents with flexible ways of making predictions about the environment. In particular, models enable planning, i.e. using more computation to improve value functions or…
We present an end-to-end Reinforcement Learning(RL) framework for robotic manipulation tasks, using a robust and efficient keypoints representation. The proposed method learns keypoints from camera images as the state representation,…
We study reinforcement learning (RL) in settings where observations are high-dimensional, but where an RL agent has access to abstract knowledge about the structure of the state space, as is the case, for example, when a robot is tasked to…
One of the fundamental challenges in reinforcement learning (RL) is the one of data efficiency: modern algorithms require a very large number of training samples, especially compared to humans, for solving environments with high-dimensional…
Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL). However, existing auxiliary tasks do not take the characteristics of RL problems…
Intelligent agents must be able to think fast and slow to perform elaborate manipulation tasks. Reinforcement Learning (RL) has led to many promising results on a range of challenging decision-making tasks. However, in real-world robotics,…
Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it…
Model-free Reinforcement Learning (RL) generally suffers from poor sample complexity, mostly due to the need to exhaustively explore the state-action space to find well-performing policies. On the other hand, we postulate that expert…
Learning-based approaches, such as reinforcement learning (RL) and imitation learning (IL), have indicated superiority over rule-based approaches in complex urban autonomous driving environments, showing great potential to make intelligent…
When Reinforcement Learning (RL) agents are deployed in practice, they might impact their environment and change its dynamics. We propose a new framework to model this phenomenon, where the current environment depends on the deployed policy…
Perceptual understanding of the scene and the relationship between its different components is important for successful completion of robotic tasks. Representation learning has been shown to be a powerful technique for this, but most of the…
Much of recent Deep Reinforcement Learning success is owed to the neural architecture's potential to learn and use effective internal representations of the world. While many current algorithms access a simulator to train with a large…
This study proposes a safe and sample-efficient reinforcement learning (RL) framework to address two major challenges in developing applicable RL algorithms: satisfying safety constraints and efficiently learning with limited samples. To…
A random recurrent neural network, called a reservoir, can be used to learn robot movements conditioned on context inputs that encode task goals. The Learning is achieved by mapping the random dynamics of the reservoir modulated by context…