AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks

Stefan Huber, Hannes Unger, Georg Schäfer, Jakob Rehrl

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace MLP policy with Chebyshev policy (degree 3)ARS · MountainCarContinuous-v0regret: 2.72 -> 0.44Improved
replace MLP policy with Chebyshev policy (degree 3)PPO · MountainCarContinuous-v0regret: 5.48 -> 1.29Improved
train Chebyshev policy with REINFORCE instead of MLP with REINFORCEREINFORCE · MountainCarContinuous-v0regret: 0.77 compared to 2.72 of ARSImproved
replace MLP policy with Chebyshev policyARS · Pendulum-v1average return: -218.3 -> -150.8Improved
replace MLP policy with Chebyshev policyPPO · Pendulum-v1average return: -176.2 -> -162.8Improved
replace MLP policy with Chebyshev policyARS · Aero 2 (real)average return: -718.4 -> -164.2Improved
replace MLP policy with Chebyshev policyPPO · Aero 2 (real)average return: -182.0 -> -55.8Improved
replace MLP policy with Chebyshev policyPPO · Aero 2 (simulation)average return: -84.6 -> -49.2Improved
replace MLP policy with Chebyshev policyARS · Aero 2 (simulation)average return: -721.8 -> -125.2Improved
reduce PPO MLP from [64,64] to [32,32] (ablation)PPO · Mountain Car (PPO MLP architectures, 20 start positions)mean return: 94.22 -> 92.60Hurt
reduce PPO MLP from [64,64] to [16,16] (ablation)PPO · Mountain Car (PPO MLP architectures, 20 start positions)mean return: 94.22 -> -0.22Hurt
train MLP policies with REINFORCE across 8 optimizers and 6 architecturesREINFORCE · Mountain Car (MLP)goal reachedHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy