AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies

Tim Seyde, Igor Gilitschenski, Wilko Schwarting, Bartolomeo Stellato, Martin Riedmiller, Markus Wulfmeier, Daniela Rus

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 3 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 Gaussian policy head with Bernoulli bang-bang headPPO, SAC, MPO, DreamerV2 · DeepMind Control Suite (8 tasks)returnNo clear effect
Use Bernoulli policy with SAC on Cartpole tasksSAC · CartpolereturnHurt
Use Bernoulli policy with DreamerV2 on Finger SpinDreamerV2 · Finger SpinreturnHurt
Add quadratic action penalty to rewardBernoulli policy · Cartpole SwingupreturnHurt
Distill converged Gaussian teacher into Bernoulli student via behavioral cloningBernoulli student · DMC domains (excluding Humanoid)returnMixed
Use Bernoulli instead of Gaussian under perturbed environment parameters (mass, morphology, friction)MPO · Real-World RL Cartpole/Walker/QuadrupedreturnNo clear effect
Use Bernoulli instead of Gaussian under sensor disturbances at transferMPO · Real-World RL disturbancesnormalized scoreNo clear effect
Use Bang-Bang policy on sparse-reward tasks without action costBang-Bang policy · Sparse Cartpole and Walkerconvergence speedImproved
Use Bang-Bang policy on sparse-reward tasks with action costBang-Bang vs Gaussian and Bang-Off-Bang · Sparse tasks with action penaltyreturnImproved
Use Bang-Bang policy on dense tasksBang-Bang vs Gaussian and Bang-Off-Bang · Cartpole Swingup, Walker Walk, Quadruped Run (dense)returnNo clear effect
Use Bang-Bang policy on pendulum swing-up without action costBang-Bang vs Gaussian · Pendulum swing-uprise timeImproved
Use Bang-Bang policy on pendulum swing-up with quadratic action costBang-Bang vs Gaussian · Pendulum swing-up with action costreturnHurt

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