Automatic Skill Acquisition in Reinforcement Learning Agents Using Connection Bridge Centrality
نویسندگان
چکیده
Incorporating skills in reinforcement learning methods results in accelerate agents learning performance. The key problem of automatic skill discovery is to find subgoal states and create skills to reach them. Among the proposed algorithms, those based on graph centrality measures have achieved precise results. In this paper we propose a new graph centrality measure for identifying subgoal states that is crucial to develop useful skills. The main advantage of the proposed centrality measure is that this measure considers both local and global information of the agent states to score them that result in identifying real subgoal states. We will show through simulations for three benchmark tasks, namely, “four-room grid world”, “taxi driver grid world” and “soccer simulation grid world” that a procedure based on the proposed centrality measure performs better than the procedure based on the other centrality measures.
منابع مشابه
A novel graphical approach to automatic abstraction in reinforcement learning
Recent researches on automatic skill acquisition in reinforcement learning have focused on subgoal discovery methods. Among them, algorithms based on graph partitioning have achieved higher performance. In this paper, we propose a new automatic skill acquisition framework based on graph partitioning approach. The main steps of this framework are identifying subgoals and discovering useful skill...
متن کاملStochastic reinforcement benefits skill acquisition.
Learning complex skills is driven by reinforcement, which facilitates both online within-session gains and retention of the acquired skills. Yet, in ecologically relevant situations, skills are often acquired when mapping between actions and rewarding outcomes is unknown to the learning agent, resulting in reinforcement schedules of a stochastic nature. Here we trained subjects on a visuomotor ...
متن کاملSkill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining
We introduce skill chaining, a skill discovery method for reinforcement learning agents in continuous domains. Skill chaining produces chains of skills leading to an end-of-task reward. We demonstrate experimentally that skill chaining is able to create appropriate skills in a challenging continuous domain and that doing so results in performance gains.
متن کاملToward the Autonomous Acquisition of Robot Skill
The design and coordination of independent specialized skill units (often called action primitives) is fundamental to modern robotics. However, a robot that must act in a complex environment over an extended period of time should do more than just use existing skills: it should learn new skills that increase its capabilities and facilitate later problem solving. Although robots exist that can l...
متن کاملImplementing Cst in Learning Layer of Csia for Higher Level of Intelligence
Development of cognitive architecture where the agents at different levels exhibit different levels of thinking. The paper primarily focus on building the skill tree at the learning layer of the architecture. These include the discovery of one’s own body, including its structure and dynamics. Also the acquisition of associated cognitive skills such as self and non-self-distinction. This can be ...
متن کامل