Learning of Non-Parametric Control Policies with High-Dimensional State Features
By Herke Van Hoof, Jan Peters, Gerhard Neumann. 2015
36 citations recorded by the source corpus.
Subfields: Reinforcement Learning, Robotics & Control
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Reinforcement Learning
- Sergey Levine
- Pieter Abbeel
- Chelsea Finn
- Jan Peters
- Shimon Whiteson
- Shixiang Shane Gu
- Gerhard Neumann
- Abhishek Gupta
In Robotics & Control
- Sergey Levine
- Jan Peters
- Gerhard Neumann
- Pieter Abbeel
- Mrinal Kalakrishnan
- Herke Van Hoof
- Martin A. Riedmiller
- Chelsea Finn
Citations in the corpus
- Benchmarking Deep Reinforcement Learning for Continuous Control (2016, neutral): “…for many of our tasks, transient behavior is of much greater interest than steady-state behavior, which agrees with previous observation by van Hoof et al. (2015), Gradient-free methods: Surprisingly, even when training deep neural network policies with thousands of parameters, CEM…”
- Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images (2015, background): “[19], as well as kernel based [20] and deep policy learning for robot control [21].”
- Path integral guided policy search (2016, background): “Pi,t as in [28], without first fitting a local policy.”
- Learning robot in-hand manipulation with tactile features (2015, methodology): “We obtained the best results by applying the following non-linear functions to sensor vectors xl and xr s1 = 2 π arctan ( π 80 |xl|1 ) , s2 = 2 π arctan ( π 80 |xr|1 ) , which scale the vector-valued sensors to single scalar values for the left and right distal sensors.”
- Stable reinforcement learning with autoencoders for tactile and visual data (2016, methodology): “Earlier work [15] showed that this approximation can be done efficiently using kernel methods.”
- Organizing Experience: a Deeper Look at Replay Mechanisms for Sample-Based Planning in Continuous State Domains (2018, background): “, 2016; Pires and Szepesvári, 2016], kernel-based RL (KBRL) [Ormoneit and Sen, 2002], and kernel mean embeddings (KME) for RL [Grunewalder et al., 2012; Van Hoof et al., 2015; Lever et al., 2016].”
- Non-parametric Policy Search with Limited Information Loss (2017, unknown): “This paper draws from our earlier conference papers (Peters et al., 2010; van Hoof et al., 2015a,b).”