相关论文: Towards Generalization and Simplicity in Continuou…

Despite the significant progress of deep reinforcement learning (RL) in solving sequential decision making problems, RL agents often overfit to training environments and struggle to adapt to new, unseen environments. This prevents robust…

We present a reinforcement learning-based solution to autonomously race on a miniature race car platform. We show that a policy that is trained purely in simulation using a relatively simple vehicle model, including model randomization, can…

Reinforcement Learning (RL) is an emerging approach to control many dynamical systems for which classical control approaches are not applicable or insufficient. However, the resultant policies may not generalize to variations in the…

Dexterous manipulation has seen remarkable progress in recent years, with policies capable of executing many complex and contact-rich tasks in simulation. However, transferring these policies from simulation to real world remains a…

This paper proposes a new design method for a stochastic control policy using a normalizing flow (NF). In reinforcement learning (RL), the policy is usually modeled as a distribution model with trainable parameters. When this…

Model-free Reinforcement Learning (RL) offers an attractive approach to learn control policies for high-dimensional systems, but its relatively poor sample complexity often forces training in simulated environments. Even in simulation,…

Biological agents learn and act intelligently in spite of a highly limited capacity to process and store information. Many real-world problems involve continuous control, which represents a difficult task for artificial intelligence agents.…

While the optimization landscape of policy gradient methods has been recently investigated for partially observed linear systems in terms of both static output feedback and dynamical controllers, they only provide convergence guarantees to…

Deep reinforcement learning enables algorithms to learn complex behavior, deal with continuous action spaces and find good strategies in environments with high dimensional state spaces. With deep reinforcement learning being an active area…

Model predictive control (MPC) provides a useful means for controlling systems with constraints, but suffers from the computational burden of repeatedly solving an optimization problem in real time. Offline (explicit) solutions for MPC…

This paper proposes a simulation-based reinforcement learning algorithm for controlling systems with uncertain and varying system parameters. While simulators are useful for safely learning control policies, the reality gap remains a major…

Recent advancement in combining trajectory optimization with function approximation (especially neural networks) shows promise in learning complex control policies for diverse tasks in robot systems. Despite their great flexibility, the…

Recent advances in behavior cloning (BC) have enabled impressive visuomotor control policies. However, these approaches are limited by the quality of human demonstrations, the manual effort required for data collection, and the diminishing…

Humans decompose novel complex tasks into simpler ones to exploit previously learned skills. Analogously, hierarchical reinforcement learning seeks to leverage lower-level policies for simple tasks to solve complex ones. However, because…

Planning methods can solve temporally extended sequential decision making problems by composing simple behaviors. However, planning requires suitable abstractions for the states and transitions, which typically need to be designed by hand.…

While reinforcement learning methods have delivered remarkable results in a number of settings, generalization, i.e., the ability to produce policies that generalize in a reliable and systematic way, has remained a challenge. The problem of…

Despite tremendous progress in dexterous manipulation, current visuomotor policies remain fundamentally limited by two challenges: they struggle to generalize under perceptual or behavioral distribution shifts, and their performance is…

Reward models trained through Reinforcement Learning from AI Feedback (RLAIF) methods frequently suffer from limited generalizability, which hinders the alignment performance of policy models. This challenge stems from various issues,…

Modern RAN operate in highly dynamic and heterogeneous environments, where hand-tuned, rule-based RRM algorithms often underperform. While RL can surpass such heuristics in constrained settings, the diversity of deployments and…

Simulation-based learning has enabled policies for precise, contact-rich tasks (e.g., robotic assembly) to reach high success rates (~80%) under high levels of observation noise and control error. Although such performance may be sufficient…