• Corpus ID: 5069655

Towards Symbolic Reinforcement Learning with Common Sense

@article{Garcez2018TowardsSR,
  title={Towards Symbolic Reinforcement Learning with Common Sense},
  author={Artur S. d'Avila Garcez and Aimore Dutra and Eduardo Alonso},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.08597}
}
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… 

Towards Interpretable Reinforcement Learning with State Abstraction Driven by External Knowledge

This work derives a rule-based variant version of the Sarsa(λ) algorithm that augments data with prior knowledge and exploits similarities among states that provides substantial gains in training speed and performance over deep q-learning, deep deterministic policy gradients, and improves stability over proximal policy optimization.

Rule-based Reinforcement Learning augmented by External Knowledge

A rule-based variant version of the Sarsa(λ) algorithm is derived, which is called Sarsarb(λ), that augments data with complex knowledge and exploits similarities among states and improves training speed compared to the Deep Qlearning (DQN) algorithm and the Deep Deterministic Policy Gradients (DDPG) algorithm.

Combining deep reinforcement learning with prior knowledge and reasoning

A new architecture to combine external knowledge and deep reinforcement learning using only visual input is presented, augmenting image input by adding environment feature information and combining two sources of decision.

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

The paper proposes to use a first-order-logic language grounded in deep neural networks to represent facts about objects and their semantics in the real world to help Reinforcement Learning agents transfer learning.

Symbolic Distillation for Learned TCP Congestion Control

A novel symbolic branching algorithm that enables the rule to be aware of the context in terms of various network conditions, eventually converting the NN policy into a symbolic tree and preserving and improving performance over state-of-the-art NN policies while being faster and simpler than a standard neural network.

Explainability in Deep Reinforcement Learning

Solving Safety Problems with Ensemble Reinforcement Learning

A Reinforcement Learning Ensemble Framework called ReLeEF is proposed, which combines decision making methods to provide a finer grained control of the agent’s behaviour while still letting it learn by interacting with the environment.

Learning Programmatically Structured Representations with Perceptor Gradients

The proposed perceptor gradients algorithm is able to learn representations that can be directly fed into a Linear-Quadratic Regulator (LQR) or a general purpose A* planner.

A Framework to Co-Optimize Robot Exploration and Task Planning in Unknown Environments

This letter designs a unified structure named subtask, which is exploited to decompose the robot exploration and planning phases, and develops a value function and a value-based scheduler to co-optimize exploration and task processing.

References

SHOWING 1-10 OF 25 REFERENCES

Towards Deep Symbolic Reinforcement Learning

It is shown that the resulting system -- though just a prototype -- learns effectively, and, by acquiring a set of symbolic rules that are easily comprehensible to humans, dramatically outperforms a conventional, fully neural DRL system on a stochastic variant of the game.

Human-level control through deep reinforcement learning

This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

Deep Reinforcement Learning: An Overview

This work discusses core RL elements, including value function, in particular, Deep Q-Network (DQN), policy, reward, model, planning, and exploration, and important mechanisms for RL, including attention and memory, unsupervised learning, transfer learning, multi-agent RL, hierarchical RL, and learning to learn.

A Deeper Look at Planning as Learning from Replay

This paper shows for the first time an exact equivalence between the sequence of value functions found by a model-based policy-evaluation method and by amodel-free method with replay, and presents a general replay method that can mimic a spectrum of methods ranging from the explicitly model-free (TD(0)) to the explicitlymodel-based (linear Dyna).

Playing Atari with Deep Reinforcement Learning

This work presents the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning, which outperforms all previous approaches on six of the games and surpasses a human expert on three of them.

Reinforcement Learning: An Introduction

This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.

Building machines that learn and think like people

It is argued that truly human-like learning and thinking machines should build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems, and harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations.

Mastering the game of Go without human knowledge

An algorithm based solely on reinforcement learning is introduced, without human data, guidance or domain knowledge beyond game rules, that achieves superhuman performance, winning 100–0 against the previously published, champion-defeating AlphaGo.

Reinforcement Learning: A Survey

Central issues of reinforcement learning are discussed, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.

Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks

A deep neural–symbolic system is proposed and evaluated, with the experimental results indicating that modularity through the use of confidence rules and knowledge insertion can be beneficial to network performance.