Useful Policy Invariant Shaping from Arbitrary Advice

BOXES: An experiment in adaptive control

Donald Michie and Roger A Chambers. 1968 · 1968

Earlier work this paper cites.

Shaping as a method for accelerating reinforcement learning. In Proceedings of the 1992 IEEE International Symposium on Intelligent Control . 554–559

Vijaykumar Gullapalli and Andrew G Barto. 1992 · 1992

Earlier work this paper cites.

Generalization in reinforcement learning: Successful examples using sparse coarse coding. In Advances in Neural Information Processing Systems . 1038–1044

Richard S Sutton. 1996 · 1996

Earlier work this paper cites.

Learning to Drive a Bicycle Using Reinforcement Learning and Shaping. In International Conference on Machine Learning , Vol. 98. 463–471

Jette Randløv and Preben Alstrøm. 1998 · 1998

Earlier work this paper cites.

Policy invariance under reward transformations: Theory and application to reward shaping. In International Conference on Machine Learning , Vol. 99. 278–287

Andrew Y Ng, Daishi Harada, and Stuart Russell. 1999 · 1999

Earlier work this paper cites.

Potential-based shaping and Q-value initialization are equivalent

Eric Wiewiora. 2003 · 2003

Earlier work this paper cites.

Principled methods for advising reinforcement learning agents. In Proceedings of the 20th International Conference on Machine Learning . 792–799

Original

Eric Wiewiora, Garrison W Cottrell, and Charles Elkan. 2003 · 2003

Earlier work this paper cites.

Heuristically Accelerated Q–Learning: a new approach to speed up Reinforcement Learning. In Brazilian Symposium on Artificial Intelligence . Springer, 245–254

Reinaldo AC Bianchi, Carlos HC Ribeiro, and Anna HR Costa. 2004 · 2004

Cited alongside, same era.

Online learning of shaping rewards in reinforcement learning

Marek Grześ and Daniel Kudenko. 2010 · 2010

Cited alongside, same era.

Dynamic potential-based reward shaping. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems . 433–440

Sam Michael Devlin and Daniel Kudenko. 2012 · 2012

Cited alongside, same era.

Reinforcement learning from simultaneous human and MDP reward. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems-Volume 1 . 475–482

W Bradley Knox and Peter Stone. 2012 · 2012

Cited alongside, same era.

Multi-objectivization of reinforcement learning problems by reward shaping. In 2014 International Joint Conference on Neural Networks . IEEE, 2315–2322

OpenAI Gym

Original

Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016 · 2016

Later among the works it cites.

Multi-objectivization and ensembles of shapings in reinforcement learning

Tim Brys, Anna Harutyunyan, Peter Vrancx, Ann Nowé, and Matthew E. Taylor. 2017 · 2017

Later among the works it cites.

Belief reward shaping in reinforcement learning. In The 32nd Conference of Association for the Advancement of Artificial Intelligence

Ofir Marom and Benjamin Rosman. 2018 · 2018

Later among the works it cites.

OpenAI Five

OpenAI. 2018 · 2018

Later among the works it cites.

Reinforcement Learning: An Introduction (second ed.)

Richard S. Sutton and Andrew G. Barto. 2018 · 2018

Later among the works it cites.

Grandmaster level in StarCraft II using multi-agent reinforcement learning