Emergence of Locomotion Behaviours in Rich Environments

  title={Emergence of Locomotion Behaviours in Rich Environments},
  author={Nicolas Heess and TB Dhruva and Srinivasan Sriram and Jay Lemmon and Josh Merel and Greg Wayne and Yuval Tassa and Tom Erez and Ziyu Wang and S. M. Ali Eslami and Martin A. Riedmiller and David Silver},
The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals. In practice, however, it is common to carefully hand-design the reward function to encourage a particular solution, or to derive it from demonstration data. In this paper explore how a rich environment can help to promote the learning of complex behavior. Specifically, we train agents in diverse environmental contexts, and find that this encourages the emergence of… CONTINUE READING
Highly Influential
This paper has highly influenced 11 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 154 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.
Showing 1-10 of 107 extracted citations

Learning symmetric and low-energy locomotion

ACM Trans. Graph. • 2018
View 5 Excerpts
Highly Influenced

Sample-efficient Policy Optimization with Stein Control Variate

ArXiv • 2017
View 6 Excerpts
Highly Influenced

Policies Modulating Trajectory Generators

CoRL • 2018
View 4 Excerpts
Highly Influenced

154 Citations

Citations per Year
Semantic Scholar estimates that this publication has 154 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 31 references

Deep reinforcement learning through policy optimization. Tutorial at Neural Information Processing Systems, 2016

Pieter Abbeel, John Schulman
URL https://nips.cc/Conferences/2016/ Schedule?showEvent=6198 • 2016
View 3 Excerpts
Highly Influenced

Deep reinforcement learning through policy optimization

Arun Nair, Praveen Srinivasan, +6 authors Stig Petersen

Similar Papers

Loading similar papers…