Related papers: Sample Factory: Egocentric 3D Control from Pixels …
Human-computer interactive systems that rely on machine learning are becoming paramount to the lives of millions of people who use digital assistants on a daily basis. Yet, further advances are limited by the availability of data and the…
We develop provably safe and convergent reinforcement learning (RL) algorithms for control of nonlinear dynamical systems, bridging the gap between the hard safety guarantees of control theory and the convergence guarantees of RL theory.…
Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences.…
Recent progress in AI and Reinforcement learning has shown great success in solving complex problems with high dimensional state spaces. However, most of these successes have been primarily in simulated environments where failure is of…
This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several…
Computational Science on large high performance computing resources is hampered by the complexity of these systems. Much of this complexity is due to low-level details on these resources that are exposed to the application and the end user.…
Learning robotic control policies in the real world gives rise to challenges in data efficiency, safety, and controlling the initial condition of the system. On the other hand, simulations are a useful alternative as they provide an…
While deep reinforcement learning excels at solving tasks where large amounts of data can be collected through virtually unlimited interaction with the environment, learning from limited interaction remains a key challenge. We posit that an…
Reinforcement learning suffers from limitations in real practices primarily due to the number of required interactions with virtual environments. It results in a challenging problem because we are implausible to obtain a local optimal…
Robotic manipulation in unstructured environments requires reliable execution under diverse conditions, yet many state-of-the-art systems still struggle with high-dimensional action spaces, sparse rewards, and slow generalization beyond…
We present a method for enabling Reinforcement Learning of motor control policies for complex skills such as dexterous manipulation. We posit that a key difficulty for training such policies is the difficulty of exploring the problem state…
Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- substantially more,…
Reinforcement learning has been demonstrated to outperform even the best humans in complex domains like video games. However, running reinforcement learning experiments on the required scale for autonomous driving is extremely difficult.…
We accelerate deep reinforcement learning-based training in visually complex 3D environments by two orders of magnitude over prior work, realizing end-to-end training speeds of over 19,000 frames of experience per second on a single GPU and…
The sample inefficiency of reinforcement learning (RL) remains a significant challenge in robotics. RL requires large-scale simulation and can still cause long training times, slowing research and innovation. This issue is particularly…
Robotic assembly is one of the oldest and most challenging applications of robotics. In other areas of robotics, such as perception and grasping, simulation has rapidly accelerated research progress, particularly when combined with modern…
Efficient exploration has presented a long-standing challenge in reinforcement learning, especially when rewards are sparse. A developmental system can overcome this difficulty by learning from both demonstrations and self-exploration.…
We present an online model-based reinforcement learning algorithm suitable for controlling complex robotic systems directly in the real world. Unlike prevailing sim-to-real pipelines that rely on extensive offline simulation and model-free…
Simulation is used extensively in autonomous systems, particularly in robotic manipulation. By far, the most common approach is to train a controller in simulation, and then use it as an initial starting point for the real system. We…
In this work we present a new agent architecture, called Reactor, which combines multiple algorithmic and architectural contributions to produce an agent with higher sample-efficiency than Prioritized Dueling DQN (Wang et al., 2016) and…