English
Related papers

Related papers: Terminal Prediction as an Auxiliary Task for Deep …

200 papers

High-precision control tasks present substantial challenges for reinforcement learning (RL) algorithms, frequently resulting in suboptimal performance attributed to network approximation inaccuracies and inadequate sample quality.These…

Machine Learning · Computer Science 2025-02-05 Donghe Chen , Yubin Peng , Tengjie Zheng , Han Wang , Chaoran Qu , Lin Cheng

In this work, we consider policy-based methods for solving the reinforcement learning problem, and establish the sample complexity guarantees. A policy-based algorithm typically consists of an actor and a critic. We consider using various…

Machine Learning · Computer Science 2023-01-16 Zaiwei Chen , Siva Theja Maguluri

Deep reinforcement learning methods attain super-human performance in a wide range of environments. Such methods are grossly inefficient, often taking orders of magnitudes more data than humans to achieve reasonable performance. We propose…

Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical…

Artificial Intelligence · Computer Science 2015-11-23 Bradly C. Stadie , Sergey Levine , Pieter Abbeel

Deep reinforcement learning has shown its success in game playing. However, 2.5D fighting games would be a challenging task to handle due to ambiguity in visual appearances like height or depth of the characters. Moreover, actions in such…

Machine Learning · Computer Science 2018-05-08 Yu-Jhe Li , Hsin-Yu Chang , Yu-Jing Lin , Po-Wei Wu , Yu-Chiang Frank Wang

This work investigates the formal policy synthesis of continuous-state stochastic dynamic systems given high-level specifications in linear temporal logic. To learn an optimal policy that maximizes the satisfaction probability, we take a…

Artificial Intelligence · Computer Science 2023-04-21 Lening Li , Zhentian Qian

Predictive auxiliary tasks have been shown to improve performance in numerous reinforcement learning works, however, this effect is still not well understood. The primary purpose of the work presented here is to investigate the impact that…

Machine Learning · Computer Science 2020-04-20 Craig Sherstan , Bilal Kartal , Pablo Hernandez-Leal , Matthew E. Taylor

Deep reinforcement learning has learned to play many games well, but failed on others. To better characterize the modes and reasons of failure of deep reinforcement learners, we test the widely used Asynchronous Actor-Critic (A2C) algorithm…

Machine Learning · Computer Science 2019-08-14 Philip Bontrager , Ahmed Khalifa , Damien Anderson , Matthew Stephenson , Christoph Salge , Julian Togelius

Data efficiency is a key challenge for deep reinforcement learning. We address this problem by using unlabeled data to pretrain an encoder which is then finetuned on a small amount of task-specific data. To encourage learning…

In recent years, deep off-policy actor-critic algorithms have become a dominant approach to reinforcement learning for continuous control. One of the primary drivers of this improved performance is the use of pessimistic value updates to…

Machine Learning · Computer Science 2022-04-07 Ted Moskovitz , Jack Parker-Holder , Aldo Pacchiano , Michael Arbel , Michael I. Jordan

Motivated by recent advance of machine learning using Deep Reinforcement Learning this paper proposes a modified architecture that produces more robust agents and speeds up the training process. Our architecture is based on Asynchronous…

Machine Learning · Computer Science 2018-04-18 Ibrahim M. Sobh , Nevin M. Darwish

TD-learning is a foundation reinforcement learning (RL) algorithm for value prediction. Critical to the accuracy of value predictions is the quality of state representations. In this work, we consider the question: how does end-to-end…

Machine Learning · Computer Science 2023-05-31 Yunhao Tang , Rémi Munos

We pose an active perception problem where an autonomous agent actively interacts with a second agent with potentially adversarial behaviors. Given the uncertainty in the intent of the other agent, the objective is to collect further…

Artificial Intelligence · Computer Science 2019-09-20 Macheng Shen , Jonathan P How

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard…

This paper addresses policy learning in non-stationary environments and games with continuous actions. Rather than the classical reward maximization mechanism, inspired by the ideas of follow-the-regularized-leader (FTRL) and mirror descent…

Machine Learning · Computer Science 2022-08-22 Rong-Jun Qin , Fan-Ming Luo , Hong Qian , Yang Yu

In this article, we explore the feasibility of applying proximal policy optimization, a state-of-the-art deep reinforcement learning algorithm for continuous control tasks, on the dual-objective problem of controlling an underactuated…

Machine Learning · Computer Science 2019-12-20 Eivind Meyer , Haakon Robinson , Adil Rasheed , Omer San

Game theory provides the gold standard for analyzing adversarial engagements, offering strong optimality guarantees. However, these guarantees often become brittle when assumptions such as perfect information are violated. Reinforcement…

Machine Learning · Computer Science 2026-03-18 Goutam Das , Michael Dorothy , Kyle Volle , Daigo Shishika

Reinforcement learning has steadily improved and outperform human in lots of traditional games since the resurgence of deep neural network. However, these success is not easy to be copied to autonomous driving because the state spaces in…

Computer Vision and Pattern Recognition · Computer Science 2019-05-21 Sen Wang , Daoyuan Jia , Xinshuo Weng

In actor-critic-based reinforcement learning algorithms such as Twin Delayed Deep Deterministic policy gradient (TD3), insufficient exploration of the spatial space can result in suboptimal policies when controlling 7-DOF robotic arms. To…

Robotics · Computer Science 2024-08-27 Wen-Han Hsieh , Jen-Yuan Chang

Most reinforcement learning algorithms are based on a key assumption that Markov decision processes (MDPs) are stationary. However, non-stationary MDPs with dynamic action space are omnipresent in real-world scenarios. Yet problems of…

Machine Learning · Computer Science 2023-04-04 Jiaqi Ye , Xiaodong Li , Pangjing Wu , Feng Wang