AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Tactical Optimism and Pessimism for Deep Reinforcement Learning

Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel, Michael Jordan

NeurIPS 2021 · Reinforcement learning › Policy gradient and actor-critic · approach: Off-policy actor-critic with expressive policies · 13 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
add TOP bandit-based optimism/pessimism switching to TD3TD3 · MuJoCo Humanoidaverage reward: 5386 -> 5899Improved
add TOP to TD3TD3 · MuJoCo HalfCheetahaverage reward: 9566 -> 13144Improved
add TOP to TD3TD3 · MuJoCo Antaverage reward: 4242 -> 6336Improved
add TOP to RADRAD · DMControl Cup, Catch 100kaverage reward: 488 -> 919Improved
add TOP to RADRAD · DMControl Walker, Walk 500kaverage reward: 771 -> 966Improved
add bandit adaptation on top of distributional critics (ablation)QR-TD3 · MuJoCo HalfCheetahaverage reward: 11170 -> 13144Improved
add distributional critics to bandit framework (ablation)ND TOP-TD3 · MuJoCo Antaverage reward: 6096 -> 6336Improved
add distributional critics to bandit framework (ablation)ND TOP-RAD · DMControl Cheetah, Run 500kaverage reward: 564 -> 803Improved
adaptive beta vs fixed Optimistic/Pessimistic (ablation)TOP · HalfCheetah and Hopperaverage rewardNo clear effect
add TOP to RAD on Finger, Spin 100kRAD · DMControl Finger, Spin 100kaverage reward: 729 -> 832Mixed
add TOP to TD3 on ReacherTD3 · MuJoCo Reacheraverage reward: -4.22 -> -3.85No clear effect

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