Reinforcement Learning
Visual Reinforcement Learning with Imagined Goals
Ashvin V. Nair, Vitchyr Pong, Murtaza Dalal, Shikhar Bahl, Steven Lin, Sergey Levine
Agents that exist persistently in the world can prepare to solve diverse tasks by setting their own goals, practicing complex behaviors, and learning about the world around them.
Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes Andrea Tirinzoni Politecnico di Milano andrea.tirinzoni@polimi.it Xiangli Chen Amazon Robotics
What policy should be employed in a Markov decision process with uncertain parameters? Robust optimization's answer to this question is to use rectangular
Iterative Value-Aware Model Learning
V alue-A ware Model Learning (V AML) is a novel framework for learning the model of the environment in Model-Based Reinforcement Learning (MBRL) [Farahmand et al., 2017a, 2016a].
Evolved Policy Gradients
Rein Houthooft, Yuhua Chen, Phillip Isola, Bradly Stadie, Filip Wolski, OpenAI Jonathan Ho, Pieter Abbeel
We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms.
Simple random search of static linear policies is competitive for reinforcement learning
Horia Mania, Aurelia Guy, Benjamin Recht
Model-free reinforcement learning aims to offer off-the-shelf solutions for controlling dynamical systems without requiring models of the system dynamics.
Learning Task Specifications from Demonstrations
Marcell Vazquez-Chanlatte, Susmit Jha, Ashish Tiwari, Mark K. Ho, Sanjit Seshia
In many settings (e.g., robotics) demonstrations provide a natural way to specify a task. For example, an agent (e.g., human expert) gives one or more demonstrations of the task from which we seek to automatically synthesize a policy for the robot to execute. Typically, one models the demonstrator as episodically operating within a dynamical system whose transition relation only depends on the current state and action (called the Markov condition). However, even if the dynamics are Markovian, many problems are naturally modeled in non-Markovian terms (see Ex 1).
Transfer of Deep Reactive Policies for MDP Planning
Aniket (Nick) Bajpai, Sankalp Garg, None
The planners use representation-specific algorithms, thus allowing themselves to be run on all domains that can be expressed in the representation.
Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces
Motoya Ohnishi, Masahiro Yukawa, Mikael Johansson, Masashi Sugiyama
Neural Information Processing Systems http://nips.cc/
Deep Reinforcement Learning of Marked Temporal Point Processes
Utkarsh Upadhyay, Abir De, Manuel Gomez Rodriguez
In doing so, we define the agent's policy using the intensity and
6f2268bd1d3d3ebaabb04d6b5d099425-Paper.pdf
Inferring intent from observed behavior has been studied extensively within the frameworks of Bayesian inverse planning and inverse reinforcement learning. These methods infer a goal or reward function that best explains the actions of the observed agent, typically a human demonstrator. Another agent can use this inferred intent to predict, imitate, or assist the human user. However, a central assumption in inverse reinforcement learning is that the demonstrator is close to optimal.