presented The conceptions of abstract default reasoning frameworks （ADRFs） and D-consequence relations are Based on representation properties of D-consequence relations, it proves that any cumulative nonmonotonic co...presented The conceptions of abstract default reasoning frameworks （ADRFs） and D-consequence relations are Based on representation properties of D-consequence relations, it proves that any cumulative nonmonotonic consequence relation with the connective-free form can be represented by ADRFs.展开更多
In recent years,reinforcement learning(RL)has shown high potential for robotic applications.However,RL heavily relies on the reward function,and the agent merely follows the policy to maximize rewards but lacks reason...In recent years,reinforcement learning(RL)has shown high potential for robotic applications.However,RL heavily relies on the reward function,and the agent merely follows the policy to maximize rewards but lacks reasoning ability.As a result,RL may not be suitable for long-horizon robotic tasks.In this paper,we propose a novel learning framework,called multiple state spaces reasoning reinforcement learning(SRRL),to endow the agent with the primary reasoning capability.First,we abstract the implicit and latent links between multiple state spaces.Then,we embed historical observations through a long short-term memory(LSTM)network to preserve long-term memories and dependencies.The proposed SRRL’s ability of abstraction and long-term memory enables agents to execute long-horizon robotic searching and planning tasks more quickly and reasonably by exploiting the correlation between radio frequency identification(RFID)sensing properties and the environment occupation map.We experimentally validate the efficacy of SRRL in a visual game-based simulation environment.Our methodology outperforms three state-of-the-art baseline schemes by significant margins.展开更多
文摘presented The conceptions of abstract default reasoning frameworks （ADRFs） and D-consequence relations are Based on representation properties of D-consequence relations, it proves that any cumulative nonmonotonic consequence relation with the connective-free form can be represented by ADRFs.
基金supported in part by the NSF under Grants ECCS-1923163 and CNS-2107190through the RFID Lab and the Wireless Engineering Research and Education Center at Auburn University,Auburn,AL,USA.
文摘In recent years,reinforcement learning(RL)has shown high potential for robotic applications.However,RL heavily relies on the reward function,and the agent merely follows the policy to maximize rewards but lacks reasoning ability.As a result,RL may not be suitable for long-horizon robotic tasks.In this paper,we propose a novel learning framework,called multiple state spaces reasoning reinforcement learning(SRRL),to endow the agent with the primary reasoning capability.First,we abstract the implicit and latent links between multiple state spaces.Then,we embed historical observations through a long short-term memory(LSTM)network to preserve long-term memories and dependencies.The proposed SRRL’s ability of abstraction and long-term memory enables agents to execute long-horizon robotic searching and planning tasks more quickly and reasonably by exploiting the correlation between radio frequency identification(RFID)sensing properties and the environment occupation map.We experimentally validate the efficacy of SRRL in a visual game-based simulation environment.Our methodology outperforms three state-of-the-art baseline schemes by significant margins.
