Papers Policy Gradient Methods
“Policy Gradient Methods” 태그가 달린 논문 382편 · 필터 해제
Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge. Common practice has been to use handcrafted dialog acts, or the output v…
Decision MakingDialogue GenerationDialogue ManagementGoal-Oriented Dialogue Systems+3Fast Efficient Hyperparameter Tuning for Policy Gradients
The performance of policy gradient methods is sensitive to hyperparameter settings that must be tuned for any new application. Widely used grid search methods for tuning hyperparameters are sample inefficient and computa…
Meta-LearningPolicy Gradient MethodsDiverse Exploration via Conjugate Policies for Policy Gradient Methods
We address the challenge of effective exploration while maintaining good performance in policy gradient methods. As a solution, we propose diverse exploration (DE) via conjugate policies. DE learns and deploys a set of c…
Policy Gradient MethodsOn-Policy Trust Region Policy Optimisation with Replay Buffers
Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies. On-policy met…
Continuous ControlDeep Reinforcement LearningPolicy Gradient Methodsreinforcement-learning+2Communication-Efficient Policy Gradient Methods for Distributed Reinforcement Learning
This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are co…
Distributed ComputingMulti-agent Reinforcement LearningPolicy Gradient Methodsreinforcement-learning+2AdaFrame: Adaptive Frame Selection for Fast Video Recognition
We present AdaFrame, a framework that adaptively selects relevant frames on a per-input basis for fast video recognition. AdaFrame contains a Long Short-Term Memory network augmented with a global memory that provides co…
Policy Gradient MethodsVideo RecognitionAn Off-policy Policy Gradient Theorem Using Emphatic Weightings
Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, …
Policy Gradient MethodsReinforcement LearningReward-estimation variance elimination in sequential decision processes
Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor…
Policy Gradient MethodsReinforcement LearningBayesian Action Decoder for Deep Multi-Agent Reinforcement Learning
When observing the actions of others, humans make inferences about why they acted as they did, and what this implies about the world; humans also use the fact that their actions will be interpreted in this manner, allowi…
DecoderMulti-agent Reinforcement LearningPolicy Gradient Methodsreinforcement-learning+2Risk-Sensitive Reinforcement Learning via Policy Gradient Search
The objective in a traditional reinforcement learning (RL) problem is to find a policy that optimizes the expected value of a performance metric such as the infinite-horizon cumulative discounted or long-run average cost…
Policy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement
Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to the actor involves a log-likelihood update…
Policy Gradient MethodsQ-LearningPolicy Gradient in Partially Observable Environments: Approximation and Convergence
Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced…
Decision MakingPolicy Gradient MethodsReinforcement LearningWhere Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods
Recent analyses of certain gradient descent optimization methods have shown that performance can degrade in some settings - such as with stochasticity or implicit momentum. In deep reinforcement learning (Deep RL), such …
continuous-controlContinuous ControlDeep Reinforcement LearningPolicy Gradient Methods+1Training for Diversity in Image Paragraph Captioning
Image paragraph captioning models aim to produce detailed descriptions of a source image. These models use similar techniques as standard image captioning models, but they have encountered issues in text generation, nota…
DiversityImage CaptioningImage Paragraph CaptioningMachine Translation+3CaLcs: Continuously Approximating Longest Common Subsequence for Sequence Level Optimization
Maximum-likelihood estimation (MLE) is one of the most widely used approaches for training structured prediction models for text-generation based natural language processing applications. However, besides exposure bias, …
Abstractive Text SummarizationImage CaptioningMachine TranslationPolicy Gradient Methods+4The wisdom of the crowd: reliable deep reinforcement learning through ensembles of Q-functions
Reinforcement learning agents learn by exploring the environment and then exploiting what they have learned. This frees the human trainers from having to know the preferred action or intrinsic value of each encountered s…
Deep Reinforcement LearningPolicy Gradient MethodsQ-Learningreinforcement-learning+2Assumption Questioning: Latent Copying and Reward Exploitation in Question Generation
Question generation is an important task for improving our ability to process natural language data, with additional challenges over other sequence transformation tasks. Recent approaches use modifications to a Seq2Seq a…
Inductive BiasMachine TranslationPolicy Gradient MethodsQuestion Generation+3Countering Language Drift via Grounding
While reinforcement learning (RL) shows a lot of promise for natural language processing—e.g. when fine-tuning natural language systems for optimizing a certain objective—there has been little investigation into potentia…
Language ModelingLanguage ModellingPolicy Gradient MethodsReinforcement Learning (RL)+2Improvements on Hindsight Learning
Sparse reward problems are one of the biggest challenges in Reinforcement Learning. Goal-directed tasks are one such sparse reward problems where a reward signal is received only when the goal is reached. One promising w…
Policy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)Image Captioning based on Deep Reinforcement Learning
Recently it has shown that the policy-gradient methods for reinforcement learning have been utilized to train deep end-to-end systems on natural language processing tasks. What's more, with the complexity of understandin…
Deep Reinforcement LearningImage CaptioningPolicy Gradient Methodsreinforcement-learning+2