Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Chitnis, Rohan"'
Autocomplete suggestions are fundamental to modern text entry systems, with applications in domains such as messaging and email composition. Typically, autocomplete suggestions are generated from a language model with a confidence threshold. However,
Externí odkaz:
http://arxiv.org/abs/2403.15502
Autor:
Sikchi, Harshit, Chitnis, Rohan, Touati, Ahmed, Geramifard, Alborz, Zhang, Amy, Niekum, Scott
Offline Goal-Conditioned Reinforcement Learning (GCRL) is tasked with learning to achieve multiple goals in an environment purely from offline datasets using sparse reward functions. Offline GCRL is pivotal for developing generalist agents capable of
Externí odkaz:
http://arxiv.org/abs/2311.02013
Autor:
Chitnis, Rohan, Xu, Yingchen, Hashemi, Bobak, Lehnert, Lucas, Dogan, Urun, Zhu, Zheqing, Delalleau, Olivier
Publikováno v:
Short version published at ICRA 2024 (https://tinyurl.com/icra24-iqltdmpc)
Model-based reinforcement learning (RL) has shown great promise due to its sample efficiency, but still struggles with long-horizon sparse-reward tasks, especially in offline settings where the agent learns from a fixed dataset. We hypothesize that m
Externí odkaz:
http://arxiv.org/abs/2306.00867
Offline reinforcement learning (RL) allows agents to learn effective, return-maximizing policies from a static dataset. Three popular algorithms for offline RL are Conservative Q-Learning (CQL), Behavior Cloning (BC), and Decision Transformer (DT), f
Externí odkaz:
http://arxiv.org/abs/2305.14550
Autor:
Chitnis, Rohan
An autonomous agent should make good decisions quickly. These two considerations --- effectiveness and efficiency --- are especially important, and often competing, when an agent plans to make decisions sequentially in long-horizon tasks. Unfortuna
Externí odkaz:
https://hdl.handle.net/1721.1/145150
Autor:
Kumar, Nishanth, McClinton, Willie, Chitnis, Rohan, Silver, Tom, Lozano-Pérez, Tomás, Kaelbling, Leslie Pack
An effective approach to solving long-horizon tasks in robotics domains with continuous state and action spaces is bilevel planning, wherein a high-level search over an abstraction of an environment is used to guide low-level decision-making. Recent
Externí odkaz:
http://arxiv.org/abs/2208.07737
Autor:
Silver, Tom, Chitnis, Rohan, Kumar, Nishanth, McClinton, Willie, Lozano-Perez, Tomas, Kaelbling, Leslie Pack, Tenenbaum, Joshua
Efficient planning in continuous state and action spaces is fundamentally hard, even when the transition model is deterministic and known. One way to alleviate this challenge is to perform bilevel planning with abstractions, where a high-level search
Externí odkaz:
http://arxiv.org/abs/2203.09634
In realistic applications of object search, robots will need to locate target objects in complex environments while coping with unreliable sensors, especially for small or hard-to-detect objects. In such settings, correlational information can be val
Externí odkaz:
http://arxiv.org/abs/2110.09991
Autor:
Gehring, Clement, Asai, Masataro, Chitnis, Rohan, Silver, Tom, Kaelbling, Leslie Pack, Sohrabi, Shirin, Katz, Michael
Recent advances in reinforcement learning (RL) have led to a growing interest in applying RL to classical planning domains or applying classical planning methods to some complex RL domains. However, the long-horizon goal-based problems found in class
Externí odkaz:
http://arxiv.org/abs/2109.14830
Autor:
Chitnis, Rohan, Silver, Tom, Tenenbaum, Joshua B., Lozano-Perez, Tomas, Kaelbling, Leslie Pack
In robotic domains, learning and planning are complicated by continuous state spaces, continuous action spaces, and long task horizons. In this work, we address these challenges with Neuro-Symbolic Relational Transition Models (NSRTs), a novel class
Externí odkaz:
http://arxiv.org/abs/2105.14074