Improved Learning of Dynamics Models for Control

By Arun Venkatraman, Roberto Capobianco, Lerrel Pinto, Martial Hebert, Daniele Nardi, J. Bagnell. 2016

41 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering, Management Science and Operations Research, 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 Artificial Intelligence

In Control and Systems Engineering

In Management Science and Operations Research

In Reinforcement Learning

In Robotics & Control

Citations in the corpus

Model-Based Reinforcement Learning for Atari (2019, methodology): “Following Bengio et al. (2015); Venkatraman et al. (2016), we mitigate this problem by randomly replacing in training some frames of the input X by the prediction from the previous step while linearly increasing the mixing probability to 100% around the middle of the ﬁrst iteration of the training…”
Imagination-Augmented Agents for Deep Reinforcement Learning (2017, background): “[42]; these models increase data efficiency, but are not used by the agent at test time.”
Model-Ensemble Trust-Region Policy Optimization (2018, background): “These methods can potentially be much more sample efﬁcient than model-free algorithms, and hence can be applied to real-world tasks where low sample complexity is crucial (Deisenroth & Rasmussen, 2011; Levine et al., 2016a; Venkatraman et al., 2017).”
An Algorithmic Perspective on Imitation Learning (2018, background): “Recent work shows the efficacy of DaD in control problems [Venkatraman et al., 2016].”
Asymmetric Actor Critic for Image-Based Robot Learning (2017, background): “Explicit full state prediction from partial observations is often impossible and this challenge is further exacerbated by the compounding error problem [16].”
Temporal Difference Models: Model-Free Deep RL for Model-Based Control (2018, neutral): “This type of prediction is similar to the prediction made by prior work on multi-step models (Mishra et al., 2017; Venkatraman et al., 2016): predict the state after τ actions.”
Information-Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving (2017, background): “x d(t+ 1)) as opposed to the multi-step prediction error. Minimizing multi-step prediction error is technically the correct objective, but considerably more difﬁcult as the problem becomes non-convex [41]. An important detail to note is that performing standard linear regression (without Tikhonov re”
Deep Local Trajectory Replanning and Control for Robot Navigation (2019, background): “Even though this is computationally more expensive, prior work suggests that it can improve imitation [57, 58].”
Learning Real-World Robot Policies by Dreaming (2018, background): “This includes Dyna [7] as well as more recent works [26], [27], [28].”
Differentiable MPC for End-to-end Planning and Control (2018, unknown): “…be generated by model-based control algorithms to guide the policy search or prime a model-free policy [Sutton, 1990, Theodorou et al., 2010, Levine and Abbeel, 2014, Gu et al., 2016b, Venkatraman et al., 2016, Levine et al., 2016, Chebotar et al., 2017, Nagabandi et al., 2017, Sun et al., 2017].”
The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach (2018, unknown): “Other related work includes Oh et al. (2015), Venkatraman et al. (2016), Kansky et al. (2017) and Racani`ere et al. (2017).”