RECORD
Bayesian Transfer Reinforcement Learning with Prior Knowledge Rules
Machine Learning · Submitted 30 Sep 2018
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Finally, we demonstrate our method for solving mazes and show that significant speed ups can be obtained.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
We propose a probabilistic framework to directly insert prior knowledge in reinforcement learning (RL) algorithms by defining the behaviour policy as a Bayesian posterior distribution. Such a posterior combines task specific information with prior knowledge, thus allowing to achieve transfer learning across tasks. The resulting method is flexible and it can be easily incorporated to any standard off-policy and on-policy algorithms, such as those based on temporal differences and policy gradients. We develop a specific instance of this Bayesian transfer RL framework by expressing prior knowledge as general deterministic rules that can be useful in a large variety of tasks, such as navigation tasks. Also, we elaborate more on recent probabilistic and entropy-regularised RL by developing a novel temporal learning algorithm and show how to combine it with Bayesian transfer RL. Finally, we demonstrate our method for solving mazes and show that significant speed ups can be obtained.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | We propose a probabilistic framework to directly insert prior knowledge in reinforcement learning (RL) algorithms by defining the behaviour policy as a Bayesian posterior distribution. | contribution 0.96 | 0.91 | 0.14 | asserted 1.00 |
| s1 | Such a posterior combines task specific information with prior knowledge, thus allowing to achieve transfer learning across tasks. | interpretation 0.47 | 0.36 | 0.15 | asserted 0.75 |
| s2 | The resulting method is flexible and it can be easily incorporated to any standard off-policy and on-policy algorithms, such as those based on temporal differences and policy gradients. | contribution 0.50 | 0.48 | 0.08 | asserted 0.96 |
| s3 | We develop a specific instance of this Bayesian transfer RL framework by expressing prior knowledge as general deterministic rules that can be useful in a large variety of tasks, such as navigation tasks. | contribution 0.68 | 0.92 | 0.08 | asserted 0.92 |
| s4 | Also, we elaborate more on recent probabilistic and entropy-regularised RL by developing a novel temporal learning algorithm and show how to combine it with Bayesian transfer RL. | contribution 0.91 | 0.90 | 0.06 | asserted 1.00 |
| s5 | Finally, we demonstrate our method for solving mazes and show that significant speed ups can be obtained. | result 0.95 | 0.96 | 0.63 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
We propose a probabilistic framework to directly insert prior knowledge in reinforcement learning (RL) algorithms by defining the behaviour policy as a Bayesian posterior distribution. Such a posterior combines task specific information with prior knowledge, thus allowing to achieve transfer learning across tasks. The resulting method is flexible and it can be easily incorporated to any standard off-policy and on-policy algorithms, such as those based on temporal differences and policy gradients. We develop a specific instance of this Bayesian transfer RL framework by expressing prior knowledge as general deterministic rules that can be useful in a large variety of tasks, such as navigation tasks. Also, we elaborate more on recent probabilistic and entropy-regularised RL by developing a novel temporal learning algorithm and show how to combine it with Bayesian transfer RL. Finally, we demonstrate our method for solving mazes and show that significant speed ups can be obtained.
Human review
How the literature uses it
2 arXiv papers cite this in 3 sentences
Papers citing it · 2 sentences without a confident label
Uses its method or tool 1 paper
-
In order to incorporate this prior knowledge into the RL agent, we introduce a Bayesian policy inspired by [ref] .
Deep Reinforcement Learning for Uplink Scheduling in NOMA-URLLC Networks · Exploiting Prior Knowledge · 0.90
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.