AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards

Yijie Guo, Jongwook Choi, Marcin Moczulski, Shengyu Feng, Samy Bengio, Mohammad Norouzi, Honglak Lee

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Reward shaping for sparse rewards · 14 citations (OpenAlex)

Read the paper

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
Use diverse trajectory-conditioned imitation instead of count-based exploration alonePPO+EXP · Montezuma's Revengescore: 12,338 -> 22,616Improved
Use diverse trajectory-conditioned imitation instead of count-based exploration alonePPO+EXP · Pitfallscore: 0 -> 12,446Improved
Use diverse trajectory-conditioned imitation instead of count-based exploration alonePPO+EXP · Venturescore: 1,817 -> 2,011Improved
Use diverse trajectory-conditioned imitation instead of high-reward self-imitationPPO+SIL · Apple-Goldaverage episode reward: 2 -> 8.5Improved
Use diverse trajectory-conditioned imitation instead of count-based exploration alonePPO+EXP · Apple-Goldaverage episode reward: 4 -> 8.5Improved
Add a count-based exploration bonus to DTSIL (ablation)DTSIL · Atari hard-exploration gamesexploration performanceImproved
Replace flexible trajectory-conditioned actions with repeated stored actions (ablation)DTRA · Atari stochastic environmentsperformanceHurt
Condition the policy on observation sequences rather than learned state-embedding sequences (ablation)DTSIL · Montezuma's Revenge with learned state representationsscore: >20,000Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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