95 citations · 378 across the 58 of their papers we have counts for
15 papers · 1 filter
Subspace Inference Enables Efficient Active Reward Learning from Preferences
Yutai Zhou, Erdem Bıyık
Reinforcement learning from human feedback (RLHF) has emerged as a powerful yet sample-inefficient approach for learning reward models from human preferences, making active learnin…
Actor-Free Continuous Control via Structurally Maximizable Q-Functions
Yigit Korkmaz, Urvi Bhuwania, Ayush Jain +1
Value-based algorithms are a cornerstone of off-policy reinforcement learning due to their simplicity and training stability. However, their use has traditionally been restricted t…
Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions
Ayush Jain, Norio Kosaka, Xinhu Li +3
In reinforcement learning, off-policy actor-critic methods like DDPG and TD3 use deterministic policy gradients: the Q-function is learned from environment data, while the actor ma…
Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation
Michelle Pan, Mariah Schrum, Vivek Myers +2
Adaptive brain stimulation can treat neurological conditions such as Parkinson's disease and post-stroke motor deficits by influencing abnormal neural activity. Because of patient…
Batch Active Learning of Reward Functions from Human Preferences
Erdem Bıyık, Nima Anari, Dorsa Sadigh
Data generation and labeling are often expensive in robot learning. Preference-based learning is a concept that enables reliable labeling by querying users with preference question…
DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
Anthony Liang, Guy Tennenholtz, Chih-wei Hsu +3
We introduce DynaMITE-RL, a meta-reinforcement learning (meta-RL) approach to approximate inference in environments where the latent state evolves at varying rates. We model episod…
Value Explicit Pretraining for Learning Transferable Representations
Kiran Lekkala, Henghui Bao, Sumedh A. Sontakke +2
Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining}…
Active Reward Learning from Online Preferences
Vivek Myers, Erdem Bıyık, Dorsa Sadigh
Robot policies need to adapt to human preferences and/or new environments. Human experts may have the domain knowledge required to help robots achieve this adaptation. However, exi…
Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction
Zhangjie Cao, Erdem Bıyık, Guy Rosman +1
Multi-agent interactions are important to model for forecasting other agents' behaviors and trajectories. At a certain time, to forecast a reasonable future trajectory, each agent…
Learning Multimodal Rewards from Rankings
Vivek Myers, Erdem Bıyık, Nima Anari +1
Learning from human feedback has shown to be a useful approach in acquiring robot reward functions. However, expert feedback is often assumed to be drawn from an underlying unimoda…
Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams
Erdem Bıyık, Anusha Lalitha, Rajarshi Saha +2
When humans collaborate with each other, they often make decisions by observing others and considering the consequences that their actions may have on the entire team, instead of g…
APReL: A Library for Active Preference-based Reward Learning Algorithms
Erdem Bıyık, Aditi Talati, Dorsa Sadigh
Reward learning is a fundamental problem in human-robot interaction to have robots that operate in alignment with what their human user wants. Many preference-based learning algori…
Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving
Zhangjie Cao, Erdem Bıyık, Woodrow Z. Wang +4
Autonomous driving has achieved significant progress in recent years, but autonomous cars are still unable to tackle high-risk situations where a potential accident is likely. In s…
Batch Active Learning Using Determinantal Point Processes
Erdem Bıyık, Kenneth Wang, Nima Anari +1
Data collection and labeling is one of the main challenges in employing machine learning algorithms in a variety of real-world applications with limited data. While active learning…
Batch Active Preference-Based Learning of Reward Functions
Erdem Bıyık, Dorsa Sadigh
Data generation and labeling are usually an expensive part of learning for robotics. While active learning methods are commonly used to tackle the former problem, preference-based…