AI Paper Atlas

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

Belief Projection-Based Reinforcement Learning for Environments with Delayed Feedback

Jangwon Kim, Hangyeol Kim, Jiwook Kang, Jongchan Baek, Soohee Han

NeurIPS 2023 · Reinforcement learning › Policy gradient and actor-critic · approach: Actor-critic theory · 1 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
BPQL (beta Q-values on original state) vs Augmented SAC, d=3SAC · HalfCheetah-v3average return: 6054.0 -> 8100.1Improved
BPQL vs Augmented SAC, d=6SAC · HalfCheetah-v3average return: 2012.6 -> 6334.6Improved
BPQL vs Augmented SAC, d=9SAC · HalfCheetah-v3average return: 1297.2 -> 5887.5Improved
BPQL vs Delayed-SAC (model-based), d=9SAC · Walker2d-v3average return: 2.6 -> 4104.3Improved
BPQL vs Augmented SAC, d=9SAC · Hopper-v3average return: 1497.8 -> 2993.4Improved
BPQL vs baselines at short delay d=3SAC · Hopper-v3average return: 2821.7 -> 2922.5No clear effect
BPQL vs Augmented SAC on InvertedPendulum, d=6 and 9SAC · InvertedPendulum-v2average return: 1000.0 -> 983.4No clear effect
Increase delay from 3 to 9 for Augmented SACAugmented SAC · HalfCheetah-v3average return: 6054.0 -> 1297.2Hurt
Increase delay from 3 to 9 for BPQLBPQL · HalfCheetah-v3average return: 8100.1 -> 5887.5Hurt
Increase Q-network hidden size (256-256 to 512, 1024, 3 layers) (ablation)Augmented SAC · delayed MuJoCoaverage returnNo clear effect
Add actuator noise (std 0.1, 0.15) to InvertedPendulumBPQL · noisy InvertedPendulum-v2average returnImproved
Extremely long delay (20 steps HalfCheetah, 25 InvertedPendulum)BPQL · HalfCheetah-v3, InvertedPendulum-v2average returnImproved

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