Search Results for author:
Found 39 papers, 17 papers with code
Prompt a Robot to Walk with Large Language Models
Large language models (LLMs) pre-trained on vast internet-scale data have showcased remarkable capabilities across diverse domains.
The CALLA Dataset: Probing LLMs' Interactive Knowledge Acquisition from Chinese Medical Literature
Recent studies have focused on constructing Instruction Fine-Tuning (IFT) data through medical knowledge graphs to enrich the interactive medical knowledge of LLMs.
DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment
Large language models (LLMs) encode a vast amount of semantic knowledge and possess remarkable understanding and reasoning capabilities.
Decentralized Motor Skill Learning for Complex Robotic Systems
Experiments on quadruped and humanoid robots demonstrate that the learned policy is robust against local motor malfunctions and can be transferred to new tasks.
Asking Before Action: Gather Information in Embodied Decision Making with Language Models
With strong capabilities of reasoning and a generic understanding of the world, Large Language Models (LLMs) have shown great potential in building versatile embodied decision making agents capable of performing diverse tasks.
Towards Generalizable Reinforcement Learning for Trade Execution
To evaluate our algorithms, we also implement a carefully designed simulator based on historical limit order book (LOB) data to provide a high-fidelity benchmark for different algorithms.
Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild
In this paper, we propose a new framework for learning robust, agile and natural legged locomotion skills over challenging terrain.
An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context
One of the key challenges in deploying RL to real-world applications is to adapt to variations of unknown environment contexts, such as changing terrains in robotic tasks and fluctuated bandwidth in congestion control.
Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward
In this paper, we consider the case where the target task is mismatched from but similar with that of the expert.
Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate
Furthermore, we build a safe RL framework to resolve constraints required by the DRC and its corresponding shield policy.
Model-based Reinforcement Learning
reinforcement-learning
+2
Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning
This paper addresses such a challenge by Decomposed Mutual INformation Optimization (DOMINO) for context learning, which explicitly learns a disentangled context to maximize the mutual information between the context and historical trajectories, while minimizing the state transition prediction error.
Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model
End-to-end autonomous driving provides a feasible way to automatically maximize overall driving system performance by directly mapping the raw pixels from a front-facing camera to control signals.
Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning
Experimental results demonstrate that our proposed method achieves policy generalization to unseen compositional tasks in a zero-shot manner.
Performance-Driven Controller Tuning via Derivative-Free Reinforcement Learning
Choosing an appropriate parameter set for the designed controller is critical for the final performance but usually requires a tedious and careful tuning process, which implies a strong need for automatic tuning methods.
A Contact-Safe Reinforcement Learning Framework for Contact-Rich Robot Manipulation
In this paper, we propose a contact-safe reinforcement learning framework for contact-rich robot manipulation, which maintains safety in both the task space and joint space.
CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
In visual control, learning transferable state representation that can transfer between different control tasks is important to reduce the training sample size.
Flow-based Recurrent Belief State Learning for POMDPs
Furthermore, we show that the learned belief states can be plugged into downstream RL algorithms to improve performance.
Reachability Constrained Reinforcement Learning
Recent studies incorporate feasible sets into CRL with energy-based methods such as control barrier function (CBF), safety index (SI), and leverage prior conservative estimations of feasible sets, which harms the performance of the learned policy.
Scale-Equivalent Distillation for Semi-Supervised Object Detection
Further, we overcome these challenges by introducing a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
Zeroth-Order Actor-Critic
The recent advanced evolution-based zeroth-order optimization methods and the policy gradient-based first-order methods are two promising alternatives to solve reinforcement learning (RL) problems with complementary advantages.
Model-Based Reinforcement Learning via Imagination with Derived Memory
Model-based reinforcement learning aims to improve the sample efficiency of policy learning by modeling the dynamics of the environment.
Model-based Reinforcement Learning
reinforcement-learning
+1
Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning
Existing methods mostly use the posterior penalty for dangerous actions, which means that the agent is not penalized until experiencing danger.
Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning
This paper proposes a novel approach that simultaneously synthesizes the energy-function-based safety certificate and learns the safe control policy with CRL.
Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian
Based on this, the penalty method is formulated as a proportional controller, and the Lagrangian method is formulated as an integral controller.
Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety
The safety constraints commonly used by existing safe reinforcement learning (RL) methods are defined only on expectation of initial states, but allow each certain state to be unsafe, which is unsatisfying for real-world safety-critical tasks.
BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite Images
With a pair of pre- and post-disaster satellite images, building damage assessment aims at predicting the extent of damage to buildings.
Ranked #1 on
2D Semantic Segmentation
on xBD
Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function
Model information can be used to predict future trajectories, so it has huge potential to avoid dangerous region when implementing reinforcement learning (RL) on real-world tasks, like autonomous driving.
Mixed Policy Gradient
MPG contains two types of PG: 1) data-driven PG, which is obtained by directly calculating the derivative of the learned Q-value function with respect to actions, and 2) model-driven PG, which is calculated using BPTT based on the model-predictive return.
Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning
Taking a control perspective, we first interpret the penalty method and the Lagrangian method as proportional feedback and integral feedback control, respectively.
Steadily Learn to Drive with Virtual Memory
Reinforcement learning has shown great potential in developing high-level autonomous driving.
A Safe Hierarchical Planning Framework for Complex Driving Scenarios based on Reinforcement Learning
To address this challenge, we propose a hierarchical behavior planning framework with a set of low-level safe controllers and a high-level reinforcement learning algorithm (H-CtRL) as a coordinator for the low-level controllers.
Model-Based Actor-Critic with Chance Constraint for Stochastic System
Safety is essential for reinforcement learning (RL) applied in real-world situations.
Efficient Deep Learning of Non-local Features for Hyperspectral Image Classification
Therefore, to incorporate the long-range contextual information, a deep fully convolutional network (FCN) with an efficient non-local module, named ENL-FCN, is proposed for HSI classification.
End-to-end Autonomous Driving Perception with Sequential Latent Representation Learning
Current autonomous driving systems are composed of a perception system and a decision system.
Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning
A sequential latent environment model is introduced and learned jointly with the reinforcement learning process.
Adaptive Probabilistic Vehicle Trajectory Prediction Through Physically Feasible Bayesian Recurrent Neural Network
Current methods for long-term trajectory prediction cannot guarantee the physical feasibility of predicted distribution.
The Design and Implementation of a Real Time Visual Search System on JD E-commerce Platform
We present the design and implementation of a visual search system for real time image retrieval on JD. com, the world's third largest and China's largest e-commerce site.
Intention-aware Long Horizon Trajectory Prediction of Surrounding Vehicles using Dual LSTM Networks
As autonomous vehicles (AVs) need to interact with other road users, it is of importance to comprehensively understand the dynamic traffic environment, especially the future possible trajectories of surrounding vehicles.
Model-free Deep Reinforcement Learning for Urban Autonomous Driving
Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions.
