Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Frazier, Spencer"'
Value alignment is the task of creating autonomous systems whose values align with those of humans. Past work has shown that stories are a potentially rich source of information on human values; however, past work has been limited to considering valu
Externí odkaz:
http://arxiv.org/abs/2212.06048
Autor:
Castricato, Louis, Havrilla, Alexander, Matiana, Shahbuland, Pieler, Michael, Ye, Anbang, Yang, Ian, Frazier, Spencer, Riedl, Mark
Controlled automated story generation seeks to generate natural language stories satisfying constraints from natural language critiques or preferences. Existing methods to control for story preference utilize prompt engineering which is labor intensi
Externí odkaz:
http://arxiv.org/abs/2210.07792
Neural language model-based approaches to automated story generation suffer from two important limitations. First, language model-based story generators generally do not work toward a given goal or ending. Second, they often lose coherence as the sto
Externí odkaz:
http://arxiv.org/abs/2112.03808
Autor:
Matiana, Shahbuland, Smith, JR, Teehan, Ryan, Castricato, Louis, Biderman, Stella, Gao, Leo, Frazier, Spencer
Recent advances in large-scale language models (Raffel et al., 2019; Brown et al., 2020) have brought significant qualitative and quantitative improvements in machine-driven text generation. Despite this, generation and evaluation of machine-generate
Externí odkaz:
http://arxiv.org/abs/2110.03111
As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally, using only a measure of task performance as feedback, can violate societal norms for acceptable behavior or cause h
Externí odkaz:
http://arxiv.org/abs/2104.09469
Automated story generation remains a difficult area of research because it lacks strong objective measures. Generated stories may be linguistically sound, but in many cases suffer poor narrative coherence required for a compelling, logically-sound st
Externí odkaz:
http://arxiv.org/abs/2104.07472
Text based games are simulations in which an agent interacts with the world purely through natural language. They typically consist of a number of puzzles interspersed with interactions with common everyday objects and locations. Deep reinforcement l
Externí odkaz:
http://arxiv.org/abs/2012.02757
Large-scale, transformer-based language models such as GPT-2 are pretrained on diverse corpora scraped from the internet. Consequently, they are prone to generating non-normative text (i.e. in violation of social norms). We introduce a technique for
Externí odkaz:
http://arxiv.org/abs/2001.08764
Value alignment is a property of an intelligent agent indicating that it can only pursue goals and activities that are beneficial to humans. Traditional approaches to value alignment use imitation learning or preference learning to infer the values o
Externí odkaz:
http://arxiv.org/abs/1912.03553
Autor:
Frazier, Spencer, Riedl, Mark
Training deep reinforcement learning agents complex behaviors in 3D virtual environments requires significant computational resources. This is especially true in environments with high degrees of aliasing, where many states share nearly identical vis
Externí odkaz:
http://arxiv.org/abs/1908.01007