Pith. sign in

REVIEW

CoachNet: An Adversarial Sampling Approach for Reinforcement 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 2101.02649 v1 pith:VZON5FMN submitted 2021-01-07 cs.LG cs.RO

CoachNet: An Adversarial Sampling Approach for Reinforcement Learning

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

Despite the recent successes of reinforcement learning in games and robotics, it is yet to become broadly practical. Sample efficiency and unreliable performance in rare but challenging scenarios are two of the major obstacles. Drawing inspiration from the effectiveness of deliberate practice for achieving expert-level human performance, we propose a new adversarial sampling approach guided by a failure predictor named "CoachNet". CoachNet is trained online along with the agent to predict the probability of failure. This probability is then used in a stochastic sampling process to guide the agent to more challenging episodes. This way, instead of wasting time on scenarios that the agent has already mastered, training is focused on the agent's "weak spots". We present the design of CoachNet, explain its underlying principles, and empirically demonstrate its effectiveness in improving sample efficiency and test-time robustness in common continuous control tasks.

discussion (0)

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