AI Paper Atlas

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

Prediction and Control in Continual Reinforcement Learning

Nishanth Anand, Doina Precup

NeurIPS 2023 · Reinforcement learning › Policy gradient and actor-critic · approach: Temporal-difference and discounting 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
Use permanent and transient value components instead of a single DQN value functionPT-DQN-0.5x · JellyBeanWorldreward rateImproved
Use permanent and transient value components instead of a single DQN value functionPT-DQN-0.5x · MinAtarreturnImproved
Use permanent and transient value components instead of a single Q-learning value functionPT-Q-learning · Tabular gridworldepisodic returnImproved
Use permanent and transient value components instead of a single Q-learning value functionPT-Q-learning · MinigridreturnImproved
Use permanent and transient value components instead of a single TD value estimatePT-TD · Prediction tasks (discrete grid, continuous grid, and Minigrid)RMSVE on the current taskImproved
Use permanent and transient value components instead of a single TD value estimatePT-TD · Prediction tasks (discrete grid, continuous grid, and Minigrid)MSE on other tasksImproved
Reset the value-function weights at each task switch instead of preserving learned estimates (ablation)TD-learning and Q-learning · Semi-continual prediction and control experimentscurrent-task prediction error / episodic returnHurt
Add a large experience replay buffer to DQN (ablation)DQN · JellyBeanWorld and MinAtar continual RL experimentsreward rate / returnHurt
Use multiple task-specific Q-value heads with a shared trunk (ablation)DQN · JellyBeanWorld and MinAtar continual RL experimentsreward rate / returnHurt
Vary the permanent-update interval k and transient decay factor λ (ablation)PT-Q-learning · Continual tabular gridworldepisodic returnMixed
Set permanent-update frequency far above or below task-switch frequency (ablation)PT-Q-learning · Continual tabular gridworldepisodic returnNo 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