Aviral Kumar

OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning

2020 · arXiv (Cornell University)

Reinforcement learning (RL) has achieved impressive performance in a variety of online settings in which an agent's ability to query the environment for transitions and rewards is effectively unlimited. However, in many practical applications, the …

One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL

2020 · arXiv (Cornell University)

While reinforcement learning algorithms can learn effective policies for complex tasks, these policies are often brittle to even minor task variations, especially when variations are not explicitly provided during training. One natural approach to this …

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

2023 · arXiv (Cornell University)

A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization from existing datasets followed by fast online fine-tuning with limited interaction. However, existing offline RL methods tend to behave poorly …

Efficient Deep Reinforcement Learning Requires Regulating Overfitting

2023 · arXiv (Cornell University)

Deep reinforcement learning algorithms that learn policies by trial-and-error must learn from limited amounts of data collected by actively interacting with the environment. While many prior works have shown that proper regularization techniques are crucial …

D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning

2024 · arXiv (Cornell University)

Offline reinforcement learning algorithms hold the promise of enabling data-driven RL methods that do not require costly or dangerous real-world exploration and benefit from large pre-collected datasets. This in turn can facilitate real-world applications, as …