Papers › Action Priors for Large Action Spaces in Robotics

Action Priors for Large Action Spaces in Robotics

11 Jan 2021arXiv:2101.04178archive 2025-07-28

Ondrej Biza, Dian Wang, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong

In robotics, it is often not possible to learn useful policies using pure model-free reinforcement learning without significant reward shaping or curriculum learning. As a consequence, many researchers rely on expert demonstrations to guide learning. However, acquiring expert demonstrations can be expensive. This paper proposes an alternative approach where the solutions of previously solved tasks are used to produce an action prior that can facilitate exploration in future tasks. The action prior is a probability distribution over actions that summarizes the set of policies found solving previous tasks. Our results indicate that this approach can be used to solve robotic manipulation problems that would otherwise be infeasible without expert demonstrations. Source code is available at \url{https://github.com/ondrejba/action_priors}.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ondrejba/action_priors officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Reinforcement Learning (RL)Robotic GraspingTransfer LearningTransfer Reinforcement Learningreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Concatenated Skip ConnectionConvolutionDQNDense ConnectionsMax PoolingQ-LearningReLUU-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections