AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

Yue Wu, Yewen Fan, Paul Pu Liang, Amos Azaria, Yuanzhi Li, Tom Mitchell

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous RL · 7 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 Read and Reward auxiliary rewardA2C · Pacman (delayed reward)game score: 452 -> 580Improved
add Read and Reward auxiliary rewardA2C · Tennis (delayed reward)game score: -23 -> -5Improved
add Read and Reward auxiliary rewardA2C · Breakout (delayed reward)game score: 2 -> 14Improved
add Read and Reward auxiliary rewardPPO · Pacman (delayed reward)game score: 204 -> 253Improved
add Read and Reward auxiliary rewardR2D1 · Pacman (delayed reward)game score: 2116 -> 3115Improved
add Read and Reward auxiliary rewardAgent57 · Pacman (delayed reward)game score: 708 -> 1000Improved
add Read and Reward auxiliary rewardAgent57 · Breakout (delayed reward)game score: 2 -> 38Improved
add Read and Reward auxiliary rewardA2C · Breakout (delayed reward, 3 seeds)game score: 2.1 -> -4.5Hurt
add Read and Reward auxiliary rewardA2C · Pacman (delayed reward, 3 seeds)game score: 387.1 -> 455.2Improved
add Read and Reward auxiliary rewardR2D1 · Pacman (delayed reward, 3 seeds)game score: 1999.2 -> 3001.3Improved
use Wikipedia gameplay text instead of official manual (ablation)Read and Reward · Tennis, Pacman, Breakoutgame score: 580 -> 580No clear effect
remove delayed reward scheduleRead and Reward with Agent57 · Atarigame scoreNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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