Pith. sign in

REVIEW

Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts

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 2003.00203 v2 pith:2ACLP4JX submitted 2020-02-29 cs.LG cs.NEcs.ROcs.SYeess.SY

Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts

classification cs.LG cs.NEcs.ROcs.SYeess.SY
keywords dynamicslearningsourcepoliciestasktransferapproachesdata
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In reinforcement learning, agents that consider the context, or current state, when selecting source policies for transfer have been shown to outperform context-free approaches. However, none of the existing approaches transfer knowledge contextually from model-based learners to a model-free learner. This could be useful, for instance, when source policies are intentionally learned on diverse simulations with plentiful data but transferred to a real-world setting with limited data. In this paper, we assume knowledge of estimated source task dynamics and policies, and common sub-goals but different dynamics. We introduce a novel deep mixture-of-experts formulation for learning state-dependent beliefs over source task dynamics that match the target dynamics using state trajectories collected from the target task. The mixture model is easy to interpret, demonstrates robustness to estimation errors in dynamics, and is compatible with most learning algorithms. We then show how this model can be incorporated into standard policy reuse frameworks, and demonstrate its effectiveness on benchmarks from OpenAI-Gym.

discussion (0)

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