Search Results for author:
Found 15 papers, 7 papers with code
TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
Although large vision-language-action (VLA) models pretrained on extensive robot datasets offer promising generalist policies for robotic learning, they still struggle with spatial-temporal dynamics in interactive robotics, making them less effective in handling complex tasks, such as manipulation.
Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets
Drawing from these findings, we propose Manipulation Centric Representation (MCR), a foundation representation learning framework capturing both visual features and the dynamics information such as actions and proprioceptions of manipulation tasks to improve manipulation centricity.
Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
Can we generate a control policy for an agent using just one demonstration of desired behaviors as a prompt, as effortlessly as creating an image from a textual description?
Is poisoning a real threat to LLM alignment? Maybe more so than you think
Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs).
ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms.
Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
In light of the burgeoning success of reinforcement learning (RL) in diverse real-world applications, considerable focus has been directed towards ensuring RL policies are robust to adversarial attacks during test time.
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks.
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
To quantify this inactivity, we adopt dormant ratio as a metric to measure inactivity in the RL agent's network.
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
To tackle this challenge, we propose GRAD, a novel game-theoretic approach that treats the temporally-coupled robust RL problem as a partially observable two-player zero-sum game.
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning
Recent studies reveal that a well-trained deep reinforcement learning (RL) policy can be particularly vulnerable to adversarial perturbations on input observations.
Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions.
Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL
Existing works on adversarial RL either use heuristics-based methods that may not find the strongest adversary, or directly train an RL-based adversary by treating the agent as a part of the environment, which can find the optimal adversary but may become intractable in a large state space.
InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
The promise of Deep Neural Network (DNN) powered Internet of Thing (IoT) devices has motivated a tremendous demand for automated solutions to enable fast development and deployment of efficient (1) DNNs equipped with instantaneous accuracy-efficiency trade-off capability to accommodate the time-varying resources at IoT devices and (2) dataflows to optimize DNNs' execution efficiency on different devices.
FDNAS: Improving Data Privacy and Model Diversity in AutoML
To further adapt for various data distributions of clients, inspired by meta-learning, a cluster Federated Direct Neural Architecture Search (CFDNAS) framework is proposed to achieve client-aware NAS, in the sense that each client can learn a tailored deep learning model for its particular data distribution.
Parallel Knowledge Transfer in Multi-Agent Reinforcement Learning
When all agents interact with the environment and learn simultaneously, how each independent agent selectively learns from other agents' behavior knowledge is a problem that we need to solve.
Multi-agent Reinforcement Learning
reinforcement-learning
+4
