Related papers: Policy Regularization on Globally Accessible State…
Imitation learning (IL) has proven effective for enabling robots to acquire visuomotor skills through expert demonstrations. However, traditional IL methods are limited by their reliance on high-quality, often scarce, expert data, and…
While reinforcement learning (RL) provides a framework for learning through trial and error, translating RL algorithms into the real world has remained challenging. A major hurdle to real-world application arises from the development of…
Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution generalization but suffer from erroneous off-policy…
Offline reinforcement learning (RL) aims to infer sequential decision policies using only offline datasets. This is a particularly difficult setup, especially when learning to achieve multiple different goals or outcomes under a given…
Autonomous UAV inspection of confined industrial infrastructure, such as ventilation ducts, demands robust navigation policies where collisions are unacceptable. While Deep Reinforcement Learning (DRL) offers a powerful paradigm for…
Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than…
In many real-world applications, reinforcement learning (RL) agents might have to solve multiple tasks, each one typically modeled via a reward function. If reward functions are expressed linearly, and the agent has previously learned a set…
Reinforcement Learning has emerged as a promising framework for developing adaptive and data-driven strategies, enabling market makers to optimize decision-making policies based on interactions with the limit order book environment. This…
We are motivated by the real challenges presented in a human-robot system to develop new designs that are efficient at data level and with performance guarantees such as stability and optimality at systems level. Existing…
Existing quadrupedal locomotion learning paradigms usually rely on extensive domain randomization to alleviate the sim2real gap and enhance robustness. It trains policies with a wide range of environment parameters and sensor noises to…
Federated reinforcement learning (FedRL) enables multiple agents to collaboratively train a global policy without sharing raw data, making it ideal for privacy-sensitive applications. However, FedRL faces challenges in heterogeneous…
Deep reinforcement learning (DRL) is one of the promising approaches for introducing robots into complicated environments. The recent remarkable progress of DRL stands on regularization of policy, which allows the policy to improve stably…
We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals. The classical approach of extracting the expert's reward function via inverse reinforcement learning, followed…
Imitation learning holds tremendous promise in learning policies efficiently for complex decision making problems. Current state-of-the-art algorithms often use inverse reinforcement learning (IRL), where given a set of expert…
We propose a novel Inverse Reinforcement Learning (IRL) method that mitigates the rigidity of fixed reward structures and the limited flexibility of implicit reward regularization. Building on the Maximum Entropy IRL framework, our approach…
Deep reinforcement learning has proven to be a powerful approach to solving control tasks, but its characteristic high-frequency oscillations make it difficult to apply in real-world environments. While prior methods have addressed action…
Reinforcement learning (RL) problems over general state and action spaces are notoriously challenging. In contrast to the tableau setting, one can not enumerate all the states and then iteratively update the policies for each state. This…
We aim to solve the problem of manipulating deformable objects, particularly elastic bands, in real-world scenarios. However, deformable object manipulation (DOM) requires a policy that works on a large state space due to the unlimited…
Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a…
We develop a simple framework to learn bio-inspired foraging policies using human data. We conduct an experiment where humans are virtually immersed in an open field foraging environment and are trained to collect the highest amount of…