Learning Online Alignments with Continuous Rewards Policy Gradient
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationQuestion Answeringspeech-recognitionSpeech RecognitionTranslationvalidSimilar Papers 제목 키워드 기반
Gradient-free Online Learning in Continuous Games with Delayed Rewards
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 SystemsDeterministic Policy Gradients With General State Transitions
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 LearningTrajectory-Oriented Policy Optimization with Sparse Rewards
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 LearningDealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies
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 GymIntrinsic Reward Policy Optimization for Sparse-Reward Environments
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