Results 1 to 10 of about 1,955,465 (354)
Value-Decomposition Multi-Agent Actor-Critics [PDF]
AAAI Conference on Artificial Intelligence, 2021 The exploitation of extra state information has been an active research area in multi-agent reinforcement learning (MARL). QMIX represents the joint action-value using a non-negative function approximator and achieves the best performance on the ...
Jianyu Su +2 more
openalex +3 more sources
Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation [PDF]
Conference on Robot Learning, 2022 Transformers have revolutionized vision and natural language processing with their ability to scale with large datasets. But in robotic manipulation, data is both limited and expensive.
Mohit Shridhar, Lucas Manuelli, D. Fox
semanticscholar +1 more source
IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies [PDF]
arXiv.org, 2023 Effective offline RL methods require properly handling out-of-distribution actions. Implicit Q-learning (IQL) addresses this by training a Q-function using only dataset actions through a modified Bellman backup.
Philippe Hansen-Estruch +4 more
semanticscholar +1 more source
Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory [PDF]
Computer Vision and Pattern Recognition, 2022 Driving 3D characters to dance following a piece of music is highly challenging due to the spatial constraints applied to poses by choreography norms.
Lian Siyao +7 more
semanticscholar +1 more source
FE or not FE? A Play in Two Acts
PRISM, 2019 The play that follows is a highly experimental work in progress. It is deliberately playful, and at times absurd, which all too often reflects the lived experiences of workers in the sector.
Gary Husband, Paul Murphy, Joel Petrie
doaj +7 more sources
, 2021 Social protection is for many international organizations a state’s affair.1 While the state definitely plays an important role, the state is by far not the only actor and there is no predefined institutional arrangement of how social protection should be implemented.
Schüring, Esther, Wiebe, Nicola
+5 more sources
Actor-Transformers for Group Activity Recognition [PDF]
Computer Vision and Pattern Recognition, 2020 This paper strives to recognize individual actions and group activities from videos. While existing solutions for this challenging problem explicitly model spatial and temporal relationships based on location of individual actors, we propose an actor ...
Kirill Gavrilyuk +3 more
semanticscholar +1 more source
ACM Transactions on Graphics, 2021 We propose Neural Actor (NA), a new method for high-quality synthesis of humans from arbitrary viewpoints and under arbitrary controllable poses.
Lingjie Liu +5 more
semanticscholar +1 more source
Frontiers in Water, 2021 Most water and development interventions aim to contribute to long-term sustainable impacts. Given the uncertainties involved in these longer-term water development projects, adaptive planning approaches hold promise to connect planning, implementation ...
Niki Versteeg +5 more
doaj +1 more source
Actor Prioritized Experience Replay [PDF]
Journal of Artificial Intelligence Research, 2022 A widely-studied deep reinforcement learning (RL) technique known as Prioritized Experience Replay (PER) allows agents to learn from transitions sampled with non-uniform probability proportional to their temporal-difference (TD) error.
Baturay Sağlam +3 more
semanticscholar +1 more source