Related papers: Learning Active Task-Oriented Exploration Policies…

Deep reinforcement learning has been shown to solve challenging tasks where large amounts of training experience is available, usually obtained online while learning the task. Robotics is a significant potential application domain for many…

Real-world robots are becoming increasingly complex and commonly act in poorly understood environments where it is extremely challenging to model or learn their true dynamics. Therefore, it might be desirable to take a task-specific…

Sim2Real aims at training policies in high-fidelity simulation environments and effectively transferring them to the real world. Despite the developments of accurate simulators and Sim2Real RL approaches, the policies trained purely in…

Achieving athletic loco-manipulation on robots requires moving beyond traditional tracking rewards - which simply guide the robot along a reference trajectory - to task rewards that drive truly dynamic, goal-oriented behaviors. Commands…

We propose a novel method for exploring the dynamics of physically based animated characters, and learning a task-agnostic action space that makes movement optimization easier. Like several previous papers, we parameterize actions as target…

How can robots learn and adapt to new tasks and situations with little data? Systematic exploration and simulation are crucial tools for efficient robot learning. We present a novel black-box policy search algorithm focused on…

A fundamental issue in reinforcement learning algorithms is the balance between exploration of the environment and exploitation of information already obtained by the agent. Especially, exploration has played a critical role for both…

Reinforcement learning encounters many challenges when applied directly in the real world. Sim-to-real transfer is widely used to transfer the knowledge learned from simulation to the real world. Domain randomization -- one of the most…

This paper proposes a novel alternative to existing sim-to-real methods for training control policies with simulated experiences. Unlike prior methods that typically rely on domain randomization over a fixed finite set of parameters, the…

Many robot manipulation tasks require active or interactive exploration behavior in order to be performed successfully. Such tasks are ubiquitous in embodied domains, where agents must actively search for the information necessary for each…

Programming a robot to deal with open-ended tasks remains a challenge, in particular if the robot has to manipulate objects. Launching, grasping, pushing or any other object interaction can be simulated but the corresponding models are not…

Dexterous manipulation has seen remarkable progress in recent years, with policies capable of executing many complex and contact-rich tasks in simulation. However, transferring these policies from simulation to real world remains a…

Simulation-to-reality transfer has emerged as a popular and highly successful method to train robotic control policies for a wide variety of tasks. However, it is often challenging to determine when policies trained in simulation are ready…

Evaluating learned robot control policies to determine their physical task-level capabilities costs experimenter time and effort. The growing number of policies and tasks exacerbates this issue. It is impractical to test every policy on…

Deep Reinforcement Learning (RL) has been explored and verified to be effective in solving decision-making tasks in various domains, such as robotics, transportation, recommender systems, etc. It learns from the interaction with…

Recently, reinforcement learning (RL) algorithms have demonstrated remarkable success in learning complicated behaviors from minimally processed input. However, most of this success is limited to simulation. While there are promising…

The field of robotics has made significant advances towards generalist robot manipulation policies. However, real-world evaluation of such policies is not scalable and faces reproducibility challenges, which are likely to worsen as policies…

Model-based reinforcement learning is an effective approach for controlling an unknown system. It is based on a longstanding pipeline familiar to the control community in which one performs experiments on the environment to collect a…

Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their…

During initial iterations of training in most Reinforcement Learning (RL) algorithms, agents perform a significant number of random exploratory steps. In the real world, this can limit the practicality of these algorithms as it can lead to…