Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach

2018-12-01 · NeurIPS 2018 12 · Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee

Potential based reward shaping is a powerful technique for accelerating convergence of reinforcement learning algorithms. Typically, such information includes an estimate of the optimal value function and is often provided by a human expert or other sources of domain knowledge. However, this information is often biased or inaccurate and can mislead many reinforcement learning algorithms. In this paper, we apply Bayesian Model Combination with multiple experts in a way that learns to trust a good combination of experts as training progresses. This approach is both computationally efficient and general, and is shown numerically to improve convergence across discrete and continuous domains and different reinforcement learning algorithms.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Evidence as Opinions of Experts

2013-03-27 · Robert Hummel, Michael Landy

We describe a viewpoint on the Dempster/Shafer 'Theory of Evidence', and provide an interpretation which regards the combination formulas as statistics of the opinions of "experts". This is done by introducing spaces wit…

Bayesian Residual Policy Optimization: Scalable Bayesian Reinforcement Learning with Clairvoyant Experts

2020-02-07 · Gilwoo Lee, Brian Hou, Sanjiban Choudhury, Siddhartha S. Srinivasa

Informed and robust decision making in the face of uncertainty is critical for robots that perform physical tasks alongside people. We formulate this as Bayesian Reinforcement Learning over latent Markov Decision Process…

Decision Making Policy Gradient Methods reinforcement-learning Reinforcement Learning+1

Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning

2022-09-22 · Paul Rolland, Luca Viano, Norman Schuerhoff, Boris Nikolov 외

While Reinforcement Learning (RL) aims to train an agent from a reward function in a given environment, Inverse Reinforcement Learning (IRL) seeks to recover the reward function from observing an expert's behavior. It is…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Optimal design of experiments to identify latent behavioral types

2018-07-10 · Stefano Balietti, Brennan Klein, Christoph Riedl

Bayesian optimal experiments that maximize the information gained from collected data are critical to efficiently identify behavioral models. We extend a seminal method for designing Bayesian optimal experiments by intro…

Decision Making Experimental Design Model Selection Reinforcement Learning

Combining Imitation and Reinforcement Learning with Free Energy Principle

2021-01-01 · Ryoya Ogishima, Izumi Karino, Yasuo Kuniyoshi

Imitation Learning (IL) and Reinforcement Learning (RL) from high dimensional sensory inputs are often introduced as separate problems, but a more realistic problem setting is how to merge the techniques so that the agen…

Imitation Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)