Related papers: Policy Stitching: Learning Transferable Robot Poli…

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…

Robotic control policies learned from human demonstrations have achieved impressive results in many real-world applications. However, in scenarios where initial performance is not satisfactory, as is often the case in novel open-world…

Achieving highly dynamic humanoid parkour on unseen, complex terrains remains a challenge in robotics. Although general locomotion policies demonstrate capabilities across broad terrain distributions, they often struggle with arbitrary and…

Recent work has shown results on learning navigation policies for idealized cylinder agents in simulation and transferring them to real wheeled robots. Deploying such navigation policies on legged robots can be challenging due to their…

We focus on developing efficient and reliable policy optimization strategies for robot learning with real-world data. In recent years, policy gradient methods have emerged as a promising paradigm for training control policies in simulation.…

Deep reinforcement learning (RL) has emerged as a promising approach for autonomously acquiring complex behaviors from low level sensor observations. Although a large portion of deep RL research has focused on applications in video games…

In recent years, industrial robots have been installed in various industries to handle advanced manufacturing and high precision tasks. However, further integration of industrial robots is hampered by their limited flexibility, adaptability…

Fully autonomous vehicles promise enhanced safety and efficiency. However, ensuring reliable operation in challenging corner cases requires control algorithms capable of performing at the vehicle limits. We address this requirement by…

The focus of this work is to enumerate the various approaches and algorithms that center around application of reinforcement learning in robotic ma- ]]nipulation tasks. Earlier methods utilized specialized policy representations and human…

We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary…

Pre-training robot policies with a rich set of skills can substantially accelerate the learning of downstream tasks. Prior works have defined pre-training tasks via natural language instructions, but doing so requires tedious human…

Reinforcement learning shows great potential to solve complex contact-rich robot manipulation tasks. However, the safety of using RL in the real world is a crucial problem, since unexpected dangerous collisions might happen when the RL…

Generating dynamic motions for legged robots remains a challenging problem. While reinforcement learning has achieved notable success in various legged locomotion tasks, producing highly dynamic behaviors often requires extensive reward…

Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task…

Generalist robot policies, trained on large and diverse datasets, have demonstrated the ability to generalize across a wide spectrum of behaviors, enabling a single policy to act in varied real-world environments. However, they still fall…

In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from…

We present a unified framework for multi-task locomotion and manipulation policy learning grounded in a contact-explicit representation. Instead of designing different policies for different tasks, our approach unifies the definition of a…

Reinforcement learning (RL) and trajectory optimization (TO) present strong complementary advantages. On one hand, RL approaches are able to learn global control policies directly from data, but generally require large sample sizes to…

Humans are capable of abstracting various tasks as different combinations of multiple attributes. This perspective of compositionality is vital for human rapid learning and adaption since previous experiences from related tasks can be…

We present a method for efficient learning of control policies for multiple related robotic motor skills. Our approach consists of two stages, joint training and specialization training. During the joint training stage, a neural network…