Related papers: Goal-conditioned Batch Reinforcement Learning for …
Offline goal-conditioned reinforcement learning (GCRL) is a promising approach for pretraining generalist policies on large datasets of reward-free trajectories, akin to the self-supervised objectives used to train foundation models for…
While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…
In offline reinforcement learning, agents are trained using only a fixed set of stored transitions derived from a source policy. However, this requires that the dataset be labeled by a reward function. In applied settings such as video game…
Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience can be acquired. This property makes these algorithms…
Understanding physical phenomena is a key component of human intelligence and enables physical interaction with previously unseen environments. In this paper, we study how an artificial agent can autonomously acquire this intuition through…
Robotic navigation in environments shared with other robots or humans remains challenging because the intentions of the surrounding agents are not directly observable and the environment conditions are continuously changing. Local…
Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…
Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that…
Humans have needs motivating their behavior according to intensity and context. However, we also create preferences associated with each action's perceived pleasure, which is susceptible to changes over time. This makes decision-making more…
The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years. However, in the domain of reinforcement learning (RL) for robot locomotion, individual skills are…
While reinforcement learning provides an appealing formalism for learning individual skills, a general-purpose robotic system must be able to master an extensive repertoire of behaviors. Instead of learning a large collection of skills…
In this paper, we propose a novel approach for agent motion prediction in cluttered environments. One of the main challenges in predicting agent motion is accounting for location and context-specific information. Our main contribution is…
We study goal-conditioned RL through the lens of generalization, but not in the traditional sense of random augmentations and domain randomization. Rather, we aim to learn goal-directed policies that generalize with respect to the horizon:…
Training reinforcement learning (RL) policies for legged locomotion often requires extensive environment interactions, which are costly and time-consuming. We propose Symmetry-Guided Memory Augmentation (SGMA), a framework that improves…
Designing reliable decision strategies for autonomous urban driving is challenging. Reinforcement learning (RL) has been used to automatically derive suitable behavior in uncertain environments, but it does not provide any guarantee on the…
When performing tasks like laundry, humans naturally coordinate both hands to manipulate objects and anticipate how their actions will change the state of the clothes. However, achieving such coordination in robotics remains challenging due…
Goal-conditioned policy learning for robotic manipulation presents significant challenges in maintaining performance across diverse objectives and environments. We introduce Hyper-GoalNet, a framework that generates task-specific policy…
We focus on the task of goal-oriented grasping, in which a robot is supposed to grasp a pre-assigned goal object in clutter and needs some pre-grasp actions such as pushes to enable stable grasps. However, in this task, the robot gets…
Parkour is a grand challenge for legged locomotion that requires robots to overcome various obstacles rapidly in complex environments. Existing methods can generate either diverse but blind locomotion skills or vision-based but specialized…
Imitation learning is an intuitive approach for teaching motion to robotic systems. Although previous studies have proposed various methods to model demonstrated movement primitives, one of the limitations of existing methods is that the…