Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining
نویسندگان
چکیده
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.
منابع مشابه
Skill Chaining: Skill Discovery in Continuous Domains
We introduce skill chaining, a skill discovery method for continuous domains. Skill chaining produces chains of skills leading to a salient event—where salience can be defined simply as an end-of-task reward, or as a more sophisticated heuristic (e.g., an intrinsically interesting event (Singh et al., 2004)). The goal of each skill in the chain is to reach a state where its successor skill can ...
متن کاملLearning Graph-Based Representations for Continuous Reinforcement Learning Domains
Graph-based domain representations have been used in discrete reinforcement learning domains as basis for, e.g., autonomous skill discovery and representation learning. These abilities are also highly relevant for learning in domains which have structured, continuous state spaces as they allow to decompose complex problems into simpler ones and reduce the burden of handengineering features. How...
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 کاملConstructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories
We introduce CST, an algorithm for constructing skill trees from demonstration trajectories in continuous reinforcement learning domains. CST uses a changepoint detection method to segment each trajectory into a skill chain by detecting a change of appropriate abstraction, or that a segment is too complex to model as a single skill. The skill chains from each trajectory are then merged to form ...
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 کامل