Zobrazeno 1 - 10
of 206
pro vyhledávání: '"Fox, Roy A."'
Recent advancements in Model-Based Reinforcement Learning (MBRL) have made it a powerful tool for visual control tasks. Despite improved data efficiency, it remains challenging to train MBRL agents with generalizable perception. Training in the prese
Externí odkaz:
http://arxiv.org/abs/2410.09972
Autor:
Kim, Kyungmin, Corsi, Davide, Rodriguez, Andoni, Lanier, JB, Parellada, Benjami, Baldi, Pierre, Sanchez, Cesar, Fox, Roy
While Deep Reinforcement Learning (DRL) has achieved remarkable success across various domains, it remains vulnerable to occasional catastrophic failures without additional safeguards. An effective solution to prevent these failures is to use a shiel
Externí odkaz:
http://arxiv.org/abs/2410.02038
In recent years, Deep Reinforcement Learning (DRL) has emerged as an effective approach to solving real-world tasks. However, despite their successes, DRL-based policies suffer from poor reliability, which limits their deployment in safety-critical d
Externí odkaz:
http://arxiv.org/abs/2406.06507
In standard reinforcement learning settings, agents typically assume immediate feedback about the effects of their actions after taking them. However, in practice, this assumption may not hold true due to physical constraints and can significantly im
Externí odkaz:
http://arxiv.org/abs/2403.12309
Backpropagation, while effective for gradient computation, falls short in addressing memory consumption, limiting scalability. This work explores forward-mode gradient computation as an alternative in invertible networks, showing its potential to red
Externí odkaz:
http://arxiv.org/abs/2402.14212
Autor:
Nottingham, Kolby, Majumder, Bodhisattwa Prasad, Mishra, Bhavana Dalvi, Singh, Sameer, Clark, Peter, Fox, Roy
Large language models (LLMs) have recently been used for sequential decision making in interactive environments. However, leveraging environment reward signals for continual LLM actor improvement is not straightforward. We propose Skill Set Optimizat
Externí odkaz:
http://arxiv.org/abs/2402.03244
Autor:
Krylov, Dmitrii, Khajeh, Pooya, Ouyang, Junhan, Reeves, Thomas, Liu, Tongkai, Ajmal, Hiba, Aghasi, Hamidreza, Fox, Roy
Automated design of analog and radio-frequency circuits using supervised or reinforcement learning from simulation data has recently been studied as an alternative to manual expert design. It is straightforward for a design agent to learn an inverse
Externí odkaz:
http://arxiv.org/abs/2307.13861
Autor:
Nottingham, Kolby, Razeghi, Yasaman, Kim, Kyungmin, Lanier, JB, Baldi, Pierre, Fox, Roy, Singh, Sameer
Large language models (LLMs) are being applied as actors for sequential decision making tasks in domains such as robotics and games, utilizing their general world knowledge and planning abilities. However, previous work does little to explore what en
Externí odkaz:
http://arxiv.org/abs/2307.11922
Autor:
Nottingham, Kolby, Ammanabrolu, Prithviraj, Suhr, Alane, Choi, Yejin, Hajishirzi, Hannaneh, Singh, Sameer, Fox, Roy
Reinforcement learning (RL) agents typically learn tabula rasa, without prior knowledge of the world. However, if initialized with knowledge of high-level subgoals and transitions between subgoals, RL agents could utilize this Abstract World Model (A
Externí odkaz:
http://arxiv.org/abs/2301.12050
Autor:
Liang, Litian, Xu, Yaosheng, McAleer, Stephen, Hu, Dailin, Ihler, Alexander, Abbeel, Pieter, Fox, Roy
Publikováno v:
ICML 2022
In temporal-difference reinforcement learning algorithms, variance in value estimation can cause instability and overestimation of the maximal target value. Many algorithms have been proposed to reduce overestimation, including several recent ensembl
Externí odkaz:
http://arxiv.org/abs/2209.07670