swMATH ID: 43034
Software Authors: Mohammadhosein Hasanbeig, Natasha Yogananda Jeppu, Alessandro Abate, Tom Melham, Daniel Kroening
Description: DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning. This paper proposes DeepSynth, a method for effective training of deep Reinforcement Learning (RL) agents when the reward is sparse and non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence of high-level objectives. Our method employs a novel algorithm for synthesis of compact automata to uncover this sequential structure automatically. We synthesise a human-interpretable automaton from trace data collected by exploring the environment. The state space of the environment is then enriched with the synthesised automaton so that the generation of a control policy by deep RL is guided by the discovered structure encoded in the automaton. The proposed approach is able to cope with both high-dimensional, low-level features and unknown sparse non-Markovian rewards. We have evaluated DeepSynth’s performance in a set of experiments that includes the Atari game Montezuma’s Revenge. Compared to existing approaches, we obtain a reduction of two orders of magnitude in the number of iterations required for policy synthesis, and also a significant improvement in scalability.
Homepage: https://arxiv.org/abs/1911.10244
Source Code:  https://github.com/grockious/deepsynth
Dependencies: Python
Related Software: AlphaZero; REINFORCEjs
Cited in: 2 Publications

Citations by Year