English
Related papers

Related papers: Backpropagation through Time and Space: Learning N…

200 papers

We study the estimation of policy gradients for continuous-time systems with known dynamics. By reframing policy learning in continuous-time, we show that it is possible construct a more efficient and accurate gradient estimator. The…

Machine Learning · Computer Science 2021-06-25 Samuel Ainsworth , Kendall Lowrey , John Thickstun , Zaid Harchaoui , Siddhartha Srinivasa

Model-based next state prediction and state value prediction are slow to converge. To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which…

Artificial Intelligence · Computer Science 2023-02-02 John Chong Min Tan , Mehul Motani

Training neural networks with reinforcement learning (RL) typically relies on backpropagation (BP), necessitating storage of activations from the forward pass for subsequent backward updates. Furthermore, backpropagating error signals…

Machine Learning · Computer Science 2025-07-16 Daniel Tanneberg

Multi-agent reinforcement learning (MARL) has become effective in tackling discrete cooperative game scenarios. However, MARL has yet to penetrate settings beyond those modelled by team and zero-sum games, confining it to a small subset of…

Multiagent Systems · Computer Science 2021-06-16 David Mguni , Yutong Wu , Yali Du , Yaodong Yang , Ziyi Wang , Minne Li , Ying Wen , Joel Jennings , Jun Wang

Recurrent neural networks (RNNs) have recently demonstrated strong performance and faster inference than Transformers at comparable parameter budgets. However, the recursive gradient computation with the backpropagation through time (or…

Machine Learning · Computer Science 2025-04-01 Paul Caillon , Erwan Fagnou , Alexandre Allauzen

Reinforcement learning-based path planning for multi-agent systems of varying size constitutes a research topic with increasing significance as progress in domains such as urban air mobility and autonomous aerial vehicles continues.…

Robotics · Computer Science 2022-03-22 Marc R. Schlichting , Stefan Notter , Walter Fichter

A technique for speeding up reinforcement learning algorithms by using time manipulation is proposed. It is applicable to failure-avoidance control problems running in a computer simulation. Turning the time of the simulation backwards on…

Artificial Intelligence · Computer Science 2009-03-31 Petar Kormushev , Kohei Nomoto , Fangyan Dong , Kaoru Hirota

Since the introduction of Alternating-time Temporal Logic (ATL), many logics have been proposed to reason about different strategic capabilities of the agents of a system. In particular, some logics have been designed to reason about the…

Logic in Computer Science · Computer Science 2017-09-08 Simon Busard , Charles Pecheur

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive)…

Artificial Intelligence · Computer Science 2017-06-20 Kamyar Azizzadenesheli , Alessandro Lazaric , Animashree Anandkumar

We study Reinforcement Learning for partially observable dynamical systems using function approximation. We propose a new \textit{Partially Observable Bilinear Actor-Critic framework}, that is general enough to include models such as…

Machine Learning · Computer Science 2022-06-27 Masatoshi Uehara , Ayush Sekhari , Jason D. Lee , Nathan Kallus , Wen Sun

Recent advances in multi-agent reinforcement learning (MARL) have demonstrated success in numerous challenging domains and environments, but typically require specialized models for each task. In this work, we propose a coherent methodology…

This paper describes experimental results regarding the real time implementation of continuous time recurrent neural networks (CTRNN) and the dynamic back-propagation through time (BPTT) algorithm for the on-line learning control laws.…

Robotics · Computer Science 2020-11-16 Patrick Henaff , Vincent Scesa , Fethi Ben Ouezdou , Olivier Bruneau

Time series modeling, a crucial area in science, often encounters challenges when training Machine Learning (ML) models like Recurrent Neural Networks (RNNs) using the conventional mini-batch training strategy that assumes independent and…

Machine Learning · Computer Science 2023-10-02 Shaoming Xu , Ankush Khandelwal , Arvind Renganathan , Vipin Kumar

We study the policy evaluation problem in multi-agent reinforcement learning where a group of agents, with jointly observed states and private local actions and rewards, collaborate to learn the value function of a given policy via local…

Optimization and Control · Mathematics 2021-11-08 Dongsheng Ding , Xiaohan Wei , Zhuoran Yang , Zhaoran Wang , Mihailo R. Jovanović

We derived a number of numerical methods to treat biomolecular systems with multiple time scales. Based on the splitting of the operators associated with the slow-varying and fast-varying forces, new multiple time-stepping (MTS) methods are…

Numerical Analysis · Mathematics 2015-01-15 Chao Liang , Xiaolan Yuan , Xiantao Li

This paper proposes a reinforcement learning method for controller synthesis of autonomous systems in unknown and partially-observable environments with subjective time-dependent safety constraints. Mathematically, we model the system…

Robotics · Computer Science 2021-04-06 Yu Wang , Alper Kamil Bozkurt , Miroslav Pajic

Deep reinforcement learning (DRL) algorithms have proven effective in robot navigation, especially in unknown environments, by directly mapping perception inputs into robot control commands. However, most existing methods ignore the local…

Robotics · Computer Science 2023-07-06 Yu'an Chen , Ruosong Ye , Ziyang Tao , Hongjian Liu , Guangda Chen , Jie Peng , Jun Ma , Yu Zhang , Jianmin Ji , Yanyong Zhang

Truncated Backpropagation Through Time (truncated BPTT) is a widespread method for learning recurrent computational graphs. Truncated BPTT keeps the computational benefits of Backpropagation Through Time (BPTT) while relieving the need for…

Neural and Evolutionary Computing · Computer Science 2017-05-24 Corentin Tallec , Yann Ollivier

Multi-agent reinforcement learning (MARL) demonstrates significant progress in solving cooperative and competitive multi-agent problems in various environments. One of the principal challenges in MARL is the need for explicit prediction of…

Machine Learning · Computer Science 2025-01-24 Alsu Sagirova , Yuri Kuratov , Mikhail Burtsev

Training recurrent neural networks is predominantly achieved via backpropagation through time (BPTT). However, this algorithm is not an optimal solution from both a biological and computational perspective. A more efficient and biologically…

Machine Learning · Computer Science 2022-10-03 Michael Hoyer , Shahram Eivazi , Sebastian Otte