Towards Symbolic Reinforcement Learning with Common Sense

04/23/2018
by   Artur d'Avila Garcez, et al.
0

Deep Reinforcement Learning (deep RL) has made several breakthroughs in recent years in applications ranging from complex control tasks in unmanned vehicles to game playing. Despite their success, deep RL still lacks several important capacities of human intelligence, such as transfer learning, abstraction and interpretability. Deep Symbolic Reinforcement Learning (DSRL) seeks to incorporate such capacities to deep Q-networks (DQN) by learning a relevant symbolic representation prior to using Q-learning. In this paper, we propose a novel extension of DSRL, which we call Symbolic Reinforcement Learning with Common Sense (SRL+CS), offering a better balance between generalization and specialization, inspired by principles of common sense when assigning rewards and aggregating Q-values. Experiments reported in this paper show that SRL+CS learns consistently faster than Q-learning and DSRL, achieving also a higher accuracy. In the hardest case, where agents were trained in a deterministic environment and tested in a random environment, SRL+CS achieves nearly 100 the best of our knowledge, this is the first case of near perfect zero-shot transfer learning using Reinforcement Learning.

READ FULL TEXT
research
01/06/2018

Faster Deep Q-learning using Neural Episodic Control

The Research on deep reinforcement learning to estimate Q-value by deep ...
research
06/15/2019

Injecting Prior Knowledge for Transfer Learning into Reinforcement Learning Algorithms using Logic Tensor Networks

Human ability at solving complex tasks is helped by priors on object and...
research
08/19/2019

Transfer in Deep Reinforcement Learning using Knowledge Graphs

Text adventure games, in which players must make sense of the world thro...
research
06/21/2021

Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming

Recently deep reinforcement learning has achieved tremendous success in ...
research
07/11/2023

Contextual Pre-Planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning

Recent studies show that deep reinforcement learning (DRL) agents tend t...
research
07/05/2023

Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning

Text-based reinforcement learning agents have predominantly been neural ...
research
08/09/2022

Intrinsically Motivated Learning of Causal World Models

Despite the recent progress in deep learning and reinforcement learning,...

Please sign up or login with your details

Forgot password? Click here to reset