Assumed Density Filtering Q-learning
December 09, 2017 ยท Entered Twilight ยท ๐ International Joint Conference on Artificial Intelligence
"Last commit was 5.0 years ago (โฅ5 year threshold)"
Evidence collected by the PWNC Scanner
Repo contents: .DS_Store, .gitignore, Dockerfile, README.md, __init__.py, classic_adfq, deep_adfq, envs, setup
Authors
Heejin Jeong, Clark Zhang, George J. Pappas, Daniel D. Lee
arXiv ID
1712.03333
Category
cs.LG: Machine Learning
Cross-listed
cs.AI
Citations
7
Venue
International Joint Conference on Artificial Intelligence
Repository
https://github.com/coco66/ADFQ.git
โญ 7
Last Checked
1 month ago
Abstract
While off-policy temporal difference (TD) methods have widely been used in reinforcement learning due to their efficiency and simple implementation, their Bayesian counterparts have not been utilized as frequently. One reason is that the non-linear max operation in the Bellman optimality equation makes it difficult to define conjugate distributions over the value functions. In this paper, we introduce a novel Bayesian approach to off-policy TD methods, called as ADFQ, which updates beliefs on state-action values, Q, through an online Bayesian inference method known as Assumed Density Filtering. We formulate an efficient closed-form solution for the value update by approximately estimating analytic parameters of the posterior of the Q-beliefs. Uncertainty measures in the beliefs not only are used in exploration but also provide a natural regularization for the value update considering all next available actions. ADFQ converges to Q-learning as the uncertainty measures of the Q-beliefs decrease and improves common drawbacks of other Bayesian RL algorithms such as computational complexity. We extend ADFQ with a neural network. Our empirical results demonstrate that ADFQ outperforms comparable algorithms on various Atari 2600 games, with drastic improvements in highly stochastic domains or domains with a large action space.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Machine Learning
R.I.P.
๐ป
Ghosted
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
R.I.P.
๐ป
Ghosted
Semi-Supervised Classification with Graph Convolutional Networks
R.I.P.
๐ป
Ghosted
Proximal Policy Optimization Algorithms
R.I.P.
๐ป
Ghosted