Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Talbott, Walter"'
Reinforcement learning practitioners often avoid hierarchical policies, especially in image-based observation spaces. Typically, the single-task performance improvement over flat-policy counterparts does not justify the additional complexity associat
Externí odkaz:
http://arxiv.org/abs/2407.19142
Step-by-step decision planning with large language models (LLMs) is gaining attention in AI agent development. This paper focuses on decision planning with uncertainty estimation to address the hallucination problem in language models. Existing appro
Externí odkaz:
http://arxiv.org/abs/2402.00251
Autor:
Szot, Andrew, Schwarzer, Max, Agrawal, Harsh, Mazoure, Bogdan, Talbott, Walter, Metcalf, Katherine, Mackraz, Natalie, Hjelm, Devon, Toshev, Alexander
We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained frozen LLM to take as input text in
Externí odkaz:
http://arxiv.org/abs/2310.17722
Autor:
Mazoure, Bogdan, Talbott, Walter, Bautista, Miguel Angel, Hjelm, Devon, Toshev, Alexander, Susskind, Josh
A fairly reliable trend in deep reinforcement learning is that the performance scales with the number of parameters, provided a complimentary scaling in amount of training data. As the appetite for large models increases, it is imperative to address,
Externí odkaz:
http://arxiv.org/abs/2306.07290
Autor:
Berthelot, David, Autef, Arnaud, Lin, Jierui, Yap, Dian Ang, Zhai, Shuangfei, Hu, Siyuan, Zheng, Daniel, Talbott, Walter, Gu, Eric
Denoising Diffusion models have demonstrated their proficiency for generative sampling. However, generating good samples often requires many iterations. Consequently, techniques such as binary time-distillation (BTD) have been proposed to reduce the
Externí odkaz:
http://arxiv.org/abs/2303.04248
Autor:
Bautista, Miguel Angel, Guo, Pengsheng, Abnar, Samira, Talbott, Walter, Toshev, Alexander, Chen, Zhuoyuan, Dinh, Laurent, Zhai, Shuangfei, Goh, Hanlin, Ulbricht, Daniel, Dehghan, Afshin, Susskind, Josh
We introduce GAUDI, a generative model capable of capturing the distribution of complex and realistic 3D scenes that can be rendered immersively from a moving camera. We tackle this challenging problem with a scalable yet powerful approach, where we
Externí odkaz:
http://arxiv.org/abs/2207.13751
Autor:
Zhai, Shuangfei, Jaitly, Navdeep, Ramapuram, Jason, Busbridge, Dan, Likhomanenko, Tatiana, Cheng, Joseph Yitan, Talbott, Walter, Huang, Chen, Goh, Hanlin, Susskind, Joshua
Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing this represe
Externí odkaz:
http://arxiv.org/abs/2207.07611
Self-attention mechanisms model long-range context by using pairwise attention between all input tokens. In doing so, they assume a fixed attention granularity defined by the individual tokens (e.g., text characters or image pixels), which may not be
Externí odkaz:
http://arxiv.org/abs/2207.01844
Learning generalizeable policies from visual input in the presence of visual distractions is a challenging problem in reinforcement learning. Recently, there has been renewed interest in bisimulation metrics as a tool to address this issue; these met
Externí odkaz:
http://arxiv.org/abs/2201.12300
Modeling the world can benefit robot learning by providing a rich training signal for shaping an agent's latent state space. However, learning world models in unconstrained environments over high-dimensional observation spaces such as images is chall
Externí odkaz:
http://arxiv.org/abs/2112.01163