Results 31 to 40 of about 34,803,504 (287)
Discriminator Augmented Model-Based Reinforcement Learning
CoRR, 2021 By planning through a learned dynamics model, model-based reinforcement learning (MBRL) offers the prospect of good performance with little environment interaction. However, it is common in practice for the learned model to be inaccurate, impairing planning and leading to poor performance. This paper aims to improve planning with an importance sampling
Behzad Haghgoo +3 more
openaire +2 more sources
Plug and Play, Model-Based Reinforcement Learning
CoRR, 2021 Sample-efficient generalisation of reinforcement learning approaches have always been a challenge, especially, for complex scenes with many components. In this work, we introduce Plug and Play Markov Decision Processes, an object-based representation that allows zero-shot integration of new objects from known object classes.
Majid Abdolshah +5 more
openaire +2 more sources
The Benefits of Model-Based Generalization in Reinforcement Learning
CoRR, 2022 Model-Based Reinforcement Learning (RL) is widely believed to have the potential to improve sample efficiency by allowing an agent to synthesize large amounts of imagined experience. Experience Replay (ER) can be considered a simple kind of model, which has proved effective at improving the stability and efficiency of deep RL.
Kenny Young +3 more
openaire +4 more sources
UAV Anti-tank Policy Training Model Based on Curriculum Reinforcement Learning [PDF]
Jisuanji kexue, 2023 In the intelligent era,the battle for land battlefield expands from planar land control to vertical land control.UAV anti-tank operation plays a crucial role in the battle for land control in future intelligent war.Deep reinforcement learning method in ...
LIN Zeyang, LAI Jun, CHEN Xiliang, WANG Jun
doaj +1 more source
Model-based Adversarial Meta-Reinforcement Learning
CoRR, 2020 Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution shift. When the test task distribution is different from the training task distribution, the performance may degrade ...
Zichuan Lin +3 more
openaire +4 more sources
Imagine to Ensure Safety in Hierarchical Reinforcement Learning
Machine Learning and Knowledge ExtractionThis work investigates the safe exploration problem in reinforcement learning, where an agent must maximize cumulative performance while simultaneously satisfying safety constraints.
Gregory Gorbov +2 more
doaj +1 more source
On the Use of Deep Reinforcement Learning for Visual Tracking: A Survey
IEEE Access, 2021 This paper aims at highlighting cutting-edge research results in the field of visual tracking by deep reinforcement learning. Deep reinforcement learning (DRL) is an emerging area combining recent progress in deep and reinforcement learning.
Giorgio Cruciata +2 more
doaj +1 more source
Decentralised demand response market model based on reinforcement learning
IET Smart Grid, 2020 A new decentralised demand response (DR) model relying on bi-directional communications is developed in this study. In this model, each user is considered as an agent that submits its bids according to the consumption urgency and a set of parameters ...
Miadreza Shafie-Khah +6 more
doaj +1 more source
Maximum Entropy Model-based Reinforcement Learning
CoRR, 2021 NeurIPS'2021 Deep Reinforcement Learning ...
Oleg Svidchenko, Aleksei Shpilman
openaire +2 more sources
On Rollouts in Model-Based Reinforcement Learning
CoRRModel-based reinforcement learning (MBRL) seeks to enhance data efficiency by learning a model of the environment and generating synthetic rollouts from it. However, accumulated model errors during these rollouts can distort the data distribution, negatively impacting policy learning and hindering long-term planning.
Bernd Frauenknecht +3 more
openaire +4 more sources