Deriving Rewards for Reinforcement Learning from Symbolic Behaviour Descriptions of Bipedal Walking
Generating physical movement behaviours from their symbolic description is a long-standing challenge in artificial intelligence (AI) and robotics, requiring insights into numerical optimization methods as well as into formalizations from symbolic AI and reasoning. In this paper, a novel approach to finding a reward function from a symbolic description is proposed. The intended system behaviour is modelled as a hybrid automaton, which reduces the system state space to allow more efficient reinforcement learning. The approach is applied to bipedal walking, by modelling the walking robot as a hybrid automaton over state space orthants, and used with the compass walker to derive a reward that incentivizes following the hybrid automaton cycle. As a result, training times of reinforcement learning controllers are reduced while final walking speed is increased. The approach can serve as a blueprint how to generate reward functions from symbolic AI and reasoning.
Code (1)
Tasks
reinforcement-learningReinforcement LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Deriving mesoscopic models of collective behaviour for finite populations
Animal groups exhibit emergent properties that are a consequence of local interactions. Linking individual-level behaviour to coarse-grained descriptions of animal groups has been a question of fundamental interest. Here…
Sentiment Analysis for Reinforcement Learning
While reinforcement learning (RL) has been successful in natural language processing (NLP) domains such as dialogue generation and text-based games, it typically faces the problem of sparse rewards that leads to slow or …
Dialogue Generationreinforcement-learningReinforcement LearningReinforcement Learning (RL)+2SymDQN: Symbolic Knowledge and Reasoning in Neural Network-based Reinforcement Learning
We propose a learning architecture that allows symbolic control and guidance in reinforcement learning with deep neural networks. We introduce SymDQN, a novel modular approach that augments the existing Dueling Deep Q-Ne…
reinforcement-learningReinforcement LearningTensor NetworksA Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments
Mental rotation -- the ability to compare objects seen from different viewpoints -- is a fundamental example of mental simulation and spatial world modeling in humans. Here we propose a mechanistic model of human mental …
Spatial ReasoningLearning Purposeful Behaviour in the Absence of Rewards
Artificial intelligence is commonly defined as the ability to achieve goals in the world. In the reinforcement learning framework, goals are encoded as reward functions that guide agent behaviour, and the sum of observed…
Reinforcement Learning