paper-with-me

홈 › Papers

Learning Online Alignments with Continuous Rewards Policy Gradient

2016-08-03 · Yuping Luo, Chung-Cheng Chiu, Navdeep Jaitly, Ilya Sutskever

Sequence-to-sequence models with soft attention had significant success in machine translation, speech recognition, and question answering. Though capable and easy to use, they require that the entirety of the input sequence is available at the beginning of inference, an assumption that is not valid for instantaneous translation and speech recognition. To address this problem, we present a new method for solving sequence-to-sequence problems using hard online alignments instead of soft offline alignments. The online alignments model is able to start producing outputs without the need to first process the entire input sequence. A highly accurate online sequence-to-sequence model is useful because it can be used to build an accurate voice-based instantaneous translator. Our model uses hard binary stochastic decisions to select the timesteps at which outputs will be produced. The model is trained to produce these stochastic decisions using a standard policy gradient method. In our experiments, we show that this model achieves encouraging performance on TIMIT and Wall Street Journal (WSJ) speech recognition datasets.

📄 PDF Abstract BibTeX arXiv:1608.01281

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationQuestion Answeringspeech-recognitionSpeech RecognitionTranslationvalid

Similar Papers 제목 키워드 기반

Gradient-free Online Learning in Continuous Games with Delayed Rewards

2020-01-01 · ICML 2020 1 · Amélie Héliou, Panayotis Mertikopoulos, Zhengyuan Zhou

Motivated by applications to online advertising and recommender systems, we consider a game-theoretic model with delayed rewards and asynchronous, payoff-based feedback. In contrast to previous work on delayed multi-arme…

Multi-Armed BanditsRecommendation Systems

Deterministic Policy Gradients With General State Transitions

2018-07-10 · Qingpeng Cai, Ling Pan, Pingzhong Tang

We study a reinforcement learning setting, where the state transition function is a convex combination of a stochastic continuous function and a deterministic function. Such a setting generalizes the widely-studied stoch…

continuous-controlContinuous ControlReinforcement Learning

Trajectory-Oriented Policy Optimization with Sparse Rewards

2024-01-04 · GuoJian Wang, Faguo Wu, Xiao Zhang

Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various explorat…

continuous-controlContinuous ControlDeep Reinforcement Learning

Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies

2022-06-12 · Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel, Pratap Tokekar 외

In this paper, we present a novel Heavy-Tailed Stochastic Policy Gradient (HT-PSG) algorithm to deal with the challenges of sparse rewards in continuous control problems. Sparse reward is common in continuous control rob…

continuous-controlContinuous ControlMuJoCoOpenAI Gym

Intrinsic Reward Policy Optimization for Sparse-Reward Environments

2026-01-29 · Minjae Cho, Huy Trong Tran arxiv

Exploration is essential in reinforcement learning as an agent relies on trial and error to learn an optimal policy. However, when rewards are sparse, naive exploration strategies, like noise injection, are often insuffi…

Reinforcement Learning