Data-Efficient Reinforcement Learning in Continuous State-Action Gaussian-POMDPs

2017-12-01 · NeurIPS 2017 12 · Rowan Mcallister, Carl Edward Rasmussen

We present a data-efficient reinforcement learning method for continuous state-action systems under significant observation noise. Data-efficient solutions under small noise exist, such as PILCO which learns the cartpole swing-up task in 30s. PILCO evaluates policies by planning state-trajectories using a dynamics model. However, PILCO applies policies to the observed state, therefore planning in observation space. We extend PILCO with filtering to instead plan in belief space, consistent with partially observable Markov decisions process (POMDP) planning. This enables data-efficient learning under significant observation noise, outperforming more naive methods such as post-hoc application of a filter to policies optimised by the original (unfiltered) PILCO algorithm. We test our method on the cartpole swing-up task, which involves nonlinear dynamics and requires nonlinear control.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Predicting Multiple Actions for Stochastic Continuous Control

2018-01-01 · ICLR 2018 1 · Sanjeev Kumar, Christian Rupprecht, Federico Tombari, Gregory D. Hager

We introduce a new approach to estimate continuous actions using actor-critic algorithms for reinforcement learning problems. Policy gradient methods usually predict one continuous action estimate or parameters of a pres…

continuous-control Continuous Control Policy Gradient Methods reinforcement-learning+2

Fast Reinforcement Learning with Incremental Gaussian Mixture Models

2020-11-02 · Rafael Pinto

This work presents a novel algorithm that integrates a data-efficient function approximator with reinforcement learning in continuous state spaces. An online and incremental algorithm capable of learning from a single pa…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution

2017-08-01 · ICML 2017 8 · Po-Wei Chou, Daniel Maturana, Sebastian Scherer

Recently, reinforcement learning with deep neural networks has achieved great success in challenging continuous control problems such as 3D locomotion and robotic manipulation. However, in real-world control problem…

continuous-control Continuous Control Deep Reinforcement Learning Reinforcement Learning

Active exploration in parameterized reinforcement learning

2016-10-06 · Mehdi Khamassi, Costas Tzafestas

Online model-free reinforcement learning (RL) methods with continuous actions are playing a prominent role when dealing with real-world applications such as Robotics. However, when confronted to non-stationary environmen…

Meta-Learning Q-Learning reinforcement-learning Reinforcement Learning+1

GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding

2025-07-21 · Fei Tang, Zhangxuan Gu, Zhengxi Lu, Xuyang Liu 외 arxiv

Graphical User Interface (GUI) grounding maps natural language instructions to precise interface locations for autonomous interaction. Current reinforcement learning approaches use binary rewards that treat elements as h…

Reinforcement Learning Binary Classification Spatial Reasoning