Pith. sign in

REVIEW

Automatic Goal Generation using Dynamical Distance Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2111.04120 v1 pith:Q7RL45ZP submitted 2021-11-07 cs.AI cs.RO

Automatic Goal Generation using Dynamical Distance Learning

classification cs.AI cs.RO
keywords taskslearningagentsdistancedynamicalefficiencygoalsample
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Reinforcement Learning (RL) agents can learn to solve complex sequential decision making tasks by interacting with the environment. However, sample efficiency remains a major challenge. In the field of multi-goal RL, where agents are required to reach multiple goals to solve complex tasks, improving sample efficiency can be especially challenging. On the other hand, humans or other biological agents learn such tasks in a much more strategic way, following a curriculum where tasks are sampled with increasing difficulty level in order to make gradual and efficient learning progress. In this work, we propose a method for automatic goal generation using a dynamical distance function (DDF) in a self-supervised fashion. DDF is a function which predicts the dynamical distance between any two states within a markov decision process (MDP). With this, we generate a curriculum of goals at the appropriate difficulty level to facilitate efficient learning throughout the training process. We evaluate this approach on several goal-conditioned robotic manipulation and navigation tasks, and show improvements in sample efficiency over a baseline method which only uses random goal sampling.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.