91 citations · 255 across the 27 of their papers we have counts for
27 papers
Prompt-Driven Exploration: Language as an Exploration Space for VLA Reinforcement Learning
Sunshine Jiang, John Marangola, David Zhang +6
Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but…
Learning from Hindsight for VLA Reinforcement Learning
Iris Xu, Sunshine Jiang, John Marangola +8
Reinforcement learning is increasingly used to fine-tune vision-language-action (VLA) models, but robot interaction is expensive and learning becomes highly sample inefficient when…
Large Pretraining Datasets Don't Guarantee Robustness after Fine-Tuning in Image Classification
Jaedong Hwang, Brian Cheung, Zhang-Wei Hong +3
Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of maintaining the general performance of the mo…
ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization
Chen Bo Calvin Zhang, Zhang-Wei Hong, Aldo Pacchiano +1
Reward shaping is critical in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. However, choosing effective shaping rewards from…
ROER: Regularized Optimal Experience Replay
Changling Li, Zhang-Wei Hong, Pulkit Agrawal +2
Experience replay serves as a key component in the success of online reinforcement learning (RL). Prioritized experience replay (PER) reweights experiences by the temporal differen…
Random Latent Exploration for Deep Reinforcement Learning
Srinath Mahankali, Zhang-Wei Hong, Ayush Sekhari +2
We introduce Random Latent Exploration (RLE), a simple yet effective exploration strategy in reinforcement learning (RL). On average, RLE outperforms noise-based methods, which per…
Curiosity-driven Red-teaming for Large Language Models
Zhang-Wei Hong, Idan Shenfeld, Tsun-Hsuan Wang +5
Large language models (LLMs) hold great potential for many natural language applications but risk generating incorrect or toxic content. To probe when an LLM generates unwanted con…
Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity
Jaedong Hwang, Zhang-Wei Hong, Eric Chen +3
Deep reinforcement learning methods exhibit impressive performance on a range of tasks but still struggle on hard exploration tasks in large environments with sparse rewards. To ad…
Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets
Zhang-Wei Hong, Aviral Kumar, Sathwik Karnik +6
Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using r…
Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building
Jaedong Hwang, Zhang-Wei Hong, Eric Chen +3
Animals and robots navigate through environments by building and refining maps of space. These maps enable functions including navigation back to home, planning, search and foragin…
TGRL: An Algorithm for Teacher Guided Reinforcement Learning
Idan Shenfeld, Zhang-Wei Hong, Aviv Tamar +1
Learning from rewards (i.e., reinforcement learning or RL) and learning to imitate a teacher (i.e., teacher-student learning) are two established approaches for solving sequential…
Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting
Zhang-Wei Hong, Pulkit Agrawal, Rémi Tachet des Combes +1
Most offline reinforcement learning (RL) algorithms return a target policy maximizing a trade-off between (1) the expected performance gain over the behavior policy that collected…
Decentralized Inference via Capability Type Structures in Cooperative Multi-Agent Systems
Charles Jin, Zhang-Wei Hong, Farid Arthaud +2
This work studies the problem of ad hoc teamwork in teams composed of agents with differing computational capabilities. We consider cooperative multi-player games in which each age…
Redeeming Intrinsic Rewards via Constrained Optimization
Eric Chen, Zhang-Wei Hong, Joni Pajarinen +1
State-of-the-art reinforcement learning (RL) algorithms typically use random sampling (e.g., -greedy) for exploration, but this method fails on hard exploration tasks like Monte…
Model Predictive Control via On-Policy Imitation Learning
Kwangjun Ahn, Zakaria Mhammedi, Horia Mania +2
In this paper, we leverage the rapid advances in imitation learning, a topic of intense recent focus in the Reinforcement Learning (RL) literature, to develop new sample complexity…
Bilinear value networks
Zhang-Wei Hong, Ge Yang, Pulkit Agrawal
The dominant framework for off-policy multi-goal reinforcement learning involves estimating goal conditioned Q-value function. When learning to achieve multiple goals, data efficie…
Stubborn: A Strong Baseline for Indoor Object Navigation
Haokuan Luo, Albert Yue, Zhang-Wei Hong +1
We present a strong baseline that surpasses the performance of previously published methods on the Habitat Challenge task of navigating to a target object in indoor environments. O…
Topological Experience Replay
Zhang-Wei Hong, Tao Chen, Yen-Chen Lin +2
State-of-the-art deep Q-learning methods update Q-values using state transition tuples sampled from the experience replay buffer. This strategy often uniformly and randomly samples…
Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture
Chin-Jui Chang, Yu-Wei Chu, Chao-Hsien Ting +3
Deep reinforcement learning (DRL) has been demonstrated to provide promising results in several challenging decision making and control tasks. However, the required inference costs…
Mixture of Step Returns in Bootstrapped DQN
Po-Han Chiang, Hsuan-Kung Yang, Zhang-Wei Hong +1
The concept of utilizing multi-step returns for updating value functions has been adopted in deep reinforcement learning (DRL) for a number of years. Updating value functions with…
Periodic Intra-Ensemble Knowledge Distillation for Reinforcement Learning
Zhang-Wei Hong, Prabhat Nagarajan, Guilherme Maeda
Off-policy ensemble reinforcement learning (RL) methods have demonstrated impressive results across a range of RL benchmark tasks. Recent works suggest that directly imitating expe…
Model-based Lookahead Reinforcement Learning
Zhang-Wei Hong, Joni Pajarinen, Jan Peters
Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics. However, despite the impressive data-efficie…
Adversarial Active Exploration for Inverse Dynamics Model Learning
Zhang-Wei Hong, Tsu-Jui Fu, Tzu-Yun Shann +2
We present an adversarial active exploration for inverse dynamics model learning, a simple yet effective learning scheme that incentivizes exploration in an environment without any…
Diversity-Driven Exploration Strategy for Deep Reinforcement Learning
Zhang-Wei Hong, Tzu-Yun Shann, Shih-Yang Su +2
Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or spars…