Related papers: Cross-Domain Transfer via Semantic Skill Imitation
Recent advances in deep reinforcement learning (RL) have demonstrated its potential to learn complex robotic manipulation tasks. However, RL still requires the robot to collect a large amount of real-world experience. To address this…
In this work, we propose several online methods to build a \emph{learning curriculum} from a given set of target-task-specific training tasks in order to speed up reinforcement learning (RL). These methods can decrease the total training…
People often watch videos on the web to learn how to cook new recipes, assemble furniture or repair a computer. We wish to enable robots with the very same capability. This is challenging; there is a large variation in manipulation actions…
In this paper, we deal with the reality gap from a novel perspective, targeting transferring Deep Reinforcement Learning (DRL) policies learned in simulated environments to the real-world domain for visual control tasks. Instead of adopting…
This work aims to learn how to perform complex robot manipulation tasks that are composed of several, consecutively executed low-level sub-tasks, given as input a few visual demonstrations of the tasks performed by a person. The sub-tasks…
In this paper, we present a new approach to Transfer Learning (TL) in Reinforcement Learning (RL) for cross-domain tasks. Many of the available techniques approach the transfer architecture as a method of speeding up the target task…
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…
Generating large-scale synthetic data in simulation is a feasible alternative to collecting/labelling real data for training vision-based deep learning models, albeit the modelling inaccuracies do not generalize to the physical world. In…
In manufacturing, assembly tasks have been a challenge for learning algorithms due to variant dynamics of different environments. Reinforcement learning (RL) is a promising framework to automatically learn these tasks, yet it is still not…
Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrated that using sparse rewards, i.e. rewarding the agent only…
Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator.…
The success of deep reinforcement learning (RL) and imitation learning (IL) in vision-based robotic manipulation typically hinges on the expense of large scale data collection. With simulation, data to train a policy can be collected…
Deep reinforcement learning has recently seen huge success across multiple areas in the robotics domain. Owing to the limitations of gathering real-world data, i.e., sample inefficiency and the cost of collecting it, simulation environments…
Transferring knowledge in cross-domain reinforcement learning is a challenging setting in which learning is accelerated by reusing knowledge from a task with different observation and/or action space. However, it is often necessary to…
Robot Imitation Learning (IL) is a widely used method for training robots to perform manipulation tasks that involve mimicking human demonstrations to acquire skills. However, its practicality has been limited due to its requirement that…
We propose an approach for inverse reinforcement learning from hetero-domain which learns a reward function in the simulator, drawing on the demonstrations from the real world. The intuition behind the method is that the reward function…
How can we imbue robots with the ability to manipulate objects precisely but also to reason about them in terms of abstract concepts? Recent works in manipulation have shown that end-to-end networks can learn dexterous skills that require…
Reinforcement Learning is a promising tool for learning complex policies even in fast-moving and object-interactive domains where human teleoperation or hard-coded policies might fail. To effectively reflect this challenging category of…
Nowadays, robots become a companion in everyday life. To be well-accepted by humans, robots should efficiently understand meanings of their partners' motions and body language, and respond accordingly. Learning concepts by imitation brings…
Recently, deep reinforcement learning (RL) has shown some impressive successes in robotic manipulation applications. However, training robots in the real world is nontrivial owing to sample efficiency and safety concerns. Sim-to-real…