English
Related papers

Related papers: Guided Policy Search as Approximate Mirror Descent

200 papers

Direct optimization is an appealing framework that replaces integration with optimization of a random objective for approximating gradients in models with discrete random variables. A$^\star$ sampling is a framework for optimizing such…

Machine Learning · Computer Science 2020-10-26 Guy Lorberbom , Chris J. Maddison , Nicolas Heess , Tamir Hazan , Daniel Tarlow

Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification…

Machine Learning · Computer Science 2023-10-24 Adrien Bolland , Gilles Louppe , Damien Ernst

Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle,…

Machine Learning · Computer Science 2020-01-01 Aviral Kumar , Xue Bin Peng , Sergey Levine

We introduce the first direct policy search algorithm which provably converges to the globally optimal $\textit{dynamic}$ filter for the classical problem of predicting the outputs of a linear dynamical system, given noisy, partial…

Optimization and Control · Mathematics 2022-03-01 Jack Umenberger , Max Simchowitz , Juan C. Perdomo , Kaiqing Zhang , Russ Tedrake

Proximal policy optimization and trust region policy optimization (PPO and TRPO) with actor and critic parametrized by neural networks achieve significant empirical success in deep reinforcement learning. However, due to nonconvexity, the…

Machine Learning · Computer Science 2023-03-01 Boyi Liu , Qi Cai , Zhuoran Yang , Zhaoran Wang

The advancement of artificial intelligence has cast a new light on the development of optimization algorithm. This paper proposes to learn a two-phase (including a minimization phase and an escaping phase) global optimization algorithm for…

Machine Learning · Computer Science 2020-03-11 Haotian Zhang , Jianyong Sun , Zongben Xu

We consider infinite-horizon discounted Markov decision problems with finite state and action spaces and study the convergence rates of the projected policy gradient method and a general class of policy mirror descent methods, all with…

Optimization and Control · Mathematics 2022-03-08 Lin Xiao

Guided Policy Search enables robots to learn control policies for complex manipulation tasks efficiently. Therein, the control policies are represented as high-dimensional neural networks which derive robot actions based on states. However,…

Robotics · Computer Science 2019-02-20 Philipp Ennen , Pia Bresenitz , Rene Vossen , Frank Hees

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…

Machine Learning · Computer Science 2020-10-23 Jorge A. Mendez , Boyu Wang , Eric Eaton

Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering. However, robotic skill learning methods typically make one of several trade-offs to…

Machine Learning · Computer Science 2016-10-07 William Montgomery , Anurag Ajay , Chelsea Finn , Pieter Abbeel , Sergey Levine

Data augmentation methods are indispensable heuristics to boost the performance of deep neural networks, especially in image recognition tasks. Recently, several studies have shown that augmentation strategies found by search algorithms…

Computer Vision and Pattern Recognition · Computer Science 2019-11-19 Ryuichiro Hataya , Jan Zdenek , Kazuki Yoshizoe , Hideki Nakayama

For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function. For example, systems that physically interact…

Machine Learning · Computer Science 2017-05-31 Joshua Achiam , David Held , Aviv Tamar , Pieter Abbeel

We propose a new policy gradient method, named homotopic policy mirror descent (HPMD), for solving discounted, infinite horizon MDPs with finite state and action spaces. HPMD performs a mirror descent type policy update with an additional…

Machine Learning · Computer Science 2022-11-30 Yan Li , Guanghui Lan , Tuo Zhao

Policy Mirror Descent (PMD) stands as a versatile algorithmic framework encompassing several seminal policy gradient algorithms such as natural policy gradient, with connections with state-of-the-art reinforcement learning (RL) algorithms…

Machine Learning · Computer Science 2024-11-07 Kimon Protopapas , Anas Barakat

Mappings to structured output spaces (strings, trees, partitions, etc.) are typically learned using extensions of classification algorithms to simple graphical structures (eg., linear chains) in which search and parameter estimation can be…

Machine Learning · Computer Science 2009-07-07 Hal Daumé , Daniel Marcu

A key problem in reinforcement learning for control with general function approximators (such as deep neural networks and other nonlinear functions) is that, for many algorithms employed in practice, updates to the policy or $Q$-function…

Machine Learning · Computer Science 2016-03-01 Joshua Achiam

Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised…

Machine Learning · Computer Science 2024-03-19 Jan Schneider , Pierre Schumacher , Simon Guist , Le Chen , Daniel Häufle , Bernhard Schölkopf , Dieter Büchler

Policy gradient methods equipped with deep neural networks have achieved great success in solving high-dimensional reinforcement learning (RL) problems. However, current analyses cannot explain why they are resistant to the curse of…

Machine Learning · Computer Science 2024-01-17 Zhenghao Xu , Xiang Ji , Minshuo Chen , Mengdi Wang , Tuo Zhao

We study how to learn $\epsilon$-optimal strategies in zero-sum imperfect information games (IIG) with trajectory feedback. In this setting, players update their policies sequentially based on their observations over a fixed number of…

Computer Science and Game Theory · Computer Science 2023-09-06 Côme Fiegel , Pierre Ménard , Tadashi Kozuno , Rémi Munos , Vianney Perchet , Michal Valko

Neuroevolution is an alternative to gradient-based optimisation that has the potential to avoid local minima and allows parallelisation. The main limiting factor is that usually it does not scale well with parameter space dimensionality.…

Machine Learning · Computer Science 2021-04-29 Nemanja Rakicevic , Antoine Cully , Petar Kormushev