Related papers: ADAPT: Zero-Shot Adaptive Policy Transfer for Stoc…
The stable combination of optimal feedback policies with online learning is studied in a new control-theoretic framework for uncertain nonlinear systems. The framework can be systematically used in transfer learning and sim-to-real…
Behavior cloning methods for robot learning suffer from poor generalization due to limited data support beyond expert demonstrations. Recent approaches leveraging video prediction models have shown promising results by learning rich…
With the explosive growth of rigid-body simulators, policy learning in simulation has become the de facto standard for most rigid morphologies. In contrast, soft robotic simulation frameworks remain scarce and are seldom adopted by the soft…
In many real-world scenarios, Reinforcement Learning (RL) algorithms are trained on data with dynamics shift, i.e., with different underlying environment dynamics. A majority of current methods address such issue by training context…
Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any…
In general-sum games, the interaction of self-interested learning agents commonly leads to socially worse outcomes, such as defect-defect in the iterated stag hunt (ISH). Previous works address this challenge by sharing rewards or shaping…
Zero-shot coordination problem in multi-agent reinforcement learning (MARL), which requires agents to adapt to unseen agents, has attracted increasing attention. Traditional approaches often rely on the Self-Play (SP) framework to generate…
We consider reinforcement learning (RL) in episodic MDPs with adversarial full-information reward feedback and unknown fixed transition kernels. We propose two model-free policy optimization algorithms, POWER and POWER++, and establish…
The composition of pretraining data is a key determinant of foundation models' performance, but there is no standard guideline for allocating a limited computational budget across different data sources. Most current approaches either rely…
We introduce PPOPT - Proximal Policy Optimization using Pretraining, a novel, model-free deep-reinforcement-learning algorithm that leverages pretraining to achieve high training efficiency and stability on very small training samples in…
We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback, employing dynamic regret as the performance measure. We start with in-depth analyses of the strengths and limitations…
We study online policy optimization in nonlinear time-varying dynamical systems where the true dynamical models are unknown to the controller. This problem is challenging because, unlike in linear systems, the controller cannot obtain…
Over these years, multi-agent reinforcement learning has achieved remarkable performance in multi-agent planning and scheduling tasks. It typically follows the self-play setting, where agents are trained by playing with a fixed group of…
Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause…
Personalizing diffusion models using limited data presents significant challenges, including overfitting, loss of prior knowledge, and degradation of text alignment. Overfitting leads to shifts in the noise prediction distribution,…
Traditional approaches in offline reinforcement learning aim to learn the optimal policy that maximizes the cumulative reward, also known as return. It is increasingly important to adjust the performance of AI agents to meet human…
We examine the problem of transferring a policy learned in a source environment to a target environment with different dynamics, particularly in the case where it is critical to reduce the amount of interaction with the target environment…
Offline safe reinforcement learning (OSRL) involves learning a decision-making policy to maximize rewards from a fixed batch of training data to satisfy pre-defined safety constraints. However, adapting to varying safety constraints during…
Robotic assembly presents a long-standing challenge due to its requirement for precise, contact-rich manipulation. While simulation-based learning has enabled the development of robust assembly policies, their performance often degrades…
Transfer learning of prediction models has been extensively studied, while the corresponding policy learning approaches are rarely discussed. In this paper, we propose principled approaches for learning the optimal policy in the target…