A review of robot learning for manipulation: Challenges, representations, and algorithms
A key challenge in intelligent robotics is creating robots that are capable of directly
interacting with the world around them to achieve their goals. The last decade has seen …
interacting with the world around them to achieve their goals. The last decade has seen …
[HTML][HTML] On the necessity of abstraction
G Konidaris - Current opinion in behavioral sciences, 2019 - Elsevier
A generally intelligent agent faces a dilemma: it requires a complex sensorimotor space to
be capable of solving a wide range of problems, but many tasks are only feasible given the …
be capable of solving a wide range of problems, but many tasks are only feasible given the …
The option-critic architecture
Temporal abstraction is key to scaling up learning and planning in reinforcement learning.
While planning with temporally extended actions is well understood, creating such …
While planning with temporally extended actions is well understood, creating such …
From skills to symbols: Learning symbolic representations for abstract high-level planning
We consider the problem of constructing abstract representations for planning in high-
dimensional, continuous environments. We assume an agent equipped with a collection of …
dimensional, continuous environments. We assume an agent equipped with a collection of …
Stochastic neural networks for hierarchical reinforcement learning
Deep reinforcement learning has achieved many impressive results in recent years.
However, tasks with sparse rewards or long horizons continue to pose significant …
However, tasks with sparse rewards or long horizons continue to pose significant …
Reinforcement learning in robotics: A survey
Reinforcement learning offers to robotics a framework and set of tools for the design of
sophisticated and hard-to-engineer behaviors. Conversely, the challenges of robotic …
sophisticated and hard-to-engineer behaviors. Conversely, the challenges of robotic …
Robot learning from demonstration by constructing skill trees
G Konidaris, S Kuindersma… - … Journal of Robotics …, 2012 - journals.sagepub.com
We describe CST, an online algorithm for constructing skill trees from demonstration
trajectories. CST segments a demonstration trajectory into a chain of component skills …
trajectories. CST segments a demonstration trajectory into a chain of component skills …
Asynchronous actor-critic for multi-agent reinforcement learning
Synchronizing decisions across multiple agents in realistic settings is problematic since it
requires agents to wait for other agents to terminate and communicate about termination …
requires agents to wait for other agents to terminate and communicate about termination …
Hrl4in: Hierarchical reinforcement learning for interactive navigation with mobile manipulators
Most common navigation tasks in human environments require auxiliary arm interactions, eg
opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks …
opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks …
Relmogen: Integrating motion generation in reinforcement learning for mobile manipulation
Many Reinforcement Learning (RL) approaches use joint control signals (positions,
velocities, torques) as action space for continuous control tasks. We propose to lift the action …
velocities, torques) as action space for continuous control tasks. We propose to lift the action …