Related papers: Skill Transfer in Deep Reinforcement Learning unde…
Accurate and robust trajectory prediction of neighboring agents is critical for autonomous vehicles traversing in complex scenes. Most methods proposed in recent years are deep learning-based due to their strength in encoding complex…
Efficient and robust policy transfer remains a key challenge for reinforcement learning to become viable for real-wold robotics. Policy transfer through warm initialization, imitation, or interacting over a large set of agents with…
In this paper, we study the Tiered Reinforcement Learning setting, a parallel transfer learning framework, where the goal is to transfer knowledge from the low-tier (source) task to the high-tier (target) task to reduce the exploration risk…
Reinforcement Learning (RL) provides a framework in which agents can be trained, via trial and error, to solve complex decision-making problems. Learning with little supervision causes RL methods to require large amounts of data, rendering…
Recently, deep reinforcement learning (RL) methods have been applied successfully to multi-agent scenarios. Typically, these methods rely on a concatenation of agent states to represent the information content required for decentralized…
Deep Reinforcement Learning has been very successful recently with various works on complex domains. Most works are concerned with learning a single policy that solves the target task, but is fixed in the sense that if the environment…
Evolutionary multitasking (EMT) algorithms typically require tailored designs for knowledge transfer, in order to assure convergence and optimality in multitask optimization. In this paper, we explore designing a systematic and…
Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. A promising approach is to learn a latent representation together with the control policy.…
Through this project, we researched on transfer learning methods and their applications on real world problems. By implementing and modifying various methods in transfer learning for our problem, we obtained an insight in the advantages and…
Humans perceive the world through multiple senses, enabling them to create a comprehensive representation of their surroundings and to generalize information across domains. For instance, when a textual description of a scene is given,…
Generalizing locomotion policies across diverse legged robots with varying morphologies is a key challenge due to differences in observation/action dimensions and system dynamics. In this work, we propose Multi-Loco, a novel unified…
Recently, a novel paradigm has been proposed for reinforcement learning-based NAS agents, that revolves around the incremental improvement of a given architecture. We assess the abilities of such reinforcement learning agents to transfer…
Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with…
Deep learning techniques are renowned for supporting effective transfer learning. However, as we demonstrate, the transferred representations support only a few modes of separation and much of its dimensionality is unutilized. In this work,…
Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new downstream tasks due to the innate task-specific training paradigm. To alleviate it, unsupervised RL, a framework that pre-trains the agent…
Deep motion forecasting models have achieved great success when trained on a massive amount of data. Yet, they often perform poorly when training data is limited. To address this challenge, we propose a transfer learning approach for…
Model-based approaches for planning and control for bipedal locomotion have a long history of success. It can provide stability and safety guarantees while being effective in accomplishing many locomotion tasks. Model-free reinforcement…
In reinforcement learning (RL), state representations are key to dealing with large or continuous state spaces. While one of the promises of deep learning algorithms is to automatically construct features well-tuned for the task they try to…
We study a Federated Reinforcement Learning (FedRL) problem in which $n$ agents collaboratively learn a single policy without sharing the trajectories they collected during agent-environment interaction. We stress the constraint of…
Frequent lane changes during congestion at freeway bottlenecks such as merge and weaving areas further reduce roadway capacity. The emergence of deep reinforcement learning (RL) and connected and automated vehicle technology provides a…