AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning to Identify Critical States for Reinforcement Learning from Videos

Haozhe Liu, Mingchen Zhuge, Bing Li, Yuhui Wang, Francesco Faccio, Bernard Ghanem, Jürgen Schmidhuber

ICCV 2023 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 10 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 compactness loss and reverse loss to importance preservation loss (ablation)Deep State Identifier detector · Grid World-SF-1 score (%): 68.98 -> 80.28Improved
add importance preservation loss to compactness + reverse loss (ablation)Deep State Identifier detector · Grid World-SF-1 score (%): 74.42 -> 80.28Improved
add compactness loss to imp + rev loss (ablation)Deep State Identifier detector · Grid World-SF-1 score (%): 76.09 -> 80.28Improved
add reverse loss to imp + compactness loss (ablation)Deep State Identifier detector · Grid World-SF-1 score (%): unstable -> 80.28Improved
use state-only input (no actions or policy) instead of EDGE with actions and policy parametersAtari-Pong-S attack · Atari-Pong-Swin rate change: -65.47 -> -77.67Improved
train detector on multiple policies instead of a single policy (ablation)Deep State Identifier · Atari-Pong cross-policy (Arch.)win rate change: -39.55 -> -76.50Improved
single-policy training evaluated on unseen policies versus random-state baseline (ablation)Deep State Identifier · Atari-Pong cross-policy (seeds)win rate change: -63.32 -> -30.67Hurt
set DQN lookahead steps from detected critical statesMulti-step DQN · Atari-Seaquestreturn: 1987.00 -> 4147.25Improved
critical-state-based n-step instead of grid-searched n-stepMulti-step DQN · Atari-Seaquestreturn: 3936.50 -> 4147.25Improved
use key-conditioned states (opening door with key)detector confidence · GridWorld-Sconfidence score: 67.13 -> 80.65Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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