No article text was recorded for this version.
policy retraining overhead
Version 1 of 169 papers70 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Learning Successor Feature Representations to Train Robust Policies for Multi-task Learning
- Blog: Uncertainty-Aware Reward-Free Exploration with General Function Approximation
- Blog: Successor Features Based Multi-Agent RL for Event-Based Decentralized MDPs
- Blog: Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs
- Blog: Universal Value Function Approximators
- Blog: Successor Feature Sets: Generalizing Successor Representations Across Policies
- Blog: Decision Tree Methods for Finding Reusable MDP Homomorphisms
- Blog: Reinforcement Learning and Deep Learning Based Lateral Control for Autonomous Driving [Application Notes]
- Blog: Flexible Locomotion Learning with Diffusion Model Predictive Control
- Blog: Reinforcement Learning with Prototypical Representations
- Blog: Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning
- Blog: URLB: Unsupervised Reinforcement Learning Benchmark
- Blog: The Termination Critic
- Blog: Successor Features for Transfer in Alternating Markov Games
- Blog: Batch Reinforcement Learning for Controlling a Mobile Wheeled Pendulum Robot
- Blog: Learning to Manipulate Object Collections Using Grounded State Representations
- Blog: Successor Features for Transfer in Reinforcement Learning
- Blog: Learning to Play With Intrinsically-Motivated, Self-Aware Agents
- Blog: Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
- Blog: Data Efficient Reinforcement Learning for Legged Robots
- Blog: Learning One Representation to Optimize All Rewards
- Blog: Artificial Intelligence and Machine Learning for Autonomous Agents that Learn to Plan and Operate in Unpredictable Dynamic Environments
- Blog: Scalar reward is not enough: a response to Silver, Singh, Precup and Sutton (2021)
- Blog: Future-conditioned Unsupervised Pretraining for Decision Transformer
- Blog: CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning
- Blog: Symbolic Plans as High-Level Instructions for Reinforcement Learning
- Blog: Goal-Conditioned Reinforcement Learning: Problems and Solutions
- Blog: Learning to Act by Predicting the Future
- Blog: Representation Discovery in Sequential Decision Making
- Blog: Proto Successor Measure: Representing the Space of All Possible Solutions of Reinforcement Learning
- Blog: Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems
- Blog: Meta-Gradient Reinforcement Learning with an Objective Discovered Online
- Blog: Proto Successor Measure: Representing the Behavior Space of an RL Agent
- Blog: Self-Supervised Reinforcement Learning that Transfers using Random Features
- Blog: Source Traces for Temporal Difference Learning
- Blog: Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
- Blog: MACS: Deep Reinforcement Learning based SDN Controller Synchronization Policy Design
- Blog: Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction
- Blog: Synthesize Policies for Transfer and Adaptation across Tasks and Environments
- Blog: Quantitative Resilience Modeling for Autonomous Cyber Defense
- Blog: Learning Parameterized Skills
- Blog: World Value Functions: Knowledge Representation for Multitask Reinforcement Learning
- Blog: Reward-Free Exploration for Reinforcement Learning
- Blog: Model-Based Offline Planning with Trajectory Pruning
- Blog: Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation
- Blog: Signal Temporal Logic Compliant Co-design of Planning and Control
- Blog: Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation
- Blog: Choreographer: Learning and Adapting Skills in Imagination
- Blog: Successor Clusters: A Behavior Basis for Unsupervised Zero-Shot Reinforcement Learning
- Blog: Adaptive Behavior Generation for Autonomous Driving using Deep Reinforcement Learning with Compact Semantic States
- Blog: Adaptable replanning with compressed linear action models for learning from demonstrations
- Blog: Learning Successor Features with Distributed Hebbian Temporal Memory
- Blog: Will it Blend? Composing Value Functions in Reinforcement Learning
- Blog: Compositional Learning-based Planning for Vision POMDPs
- Blog: Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation
- Blog: Intrinsically Motivated Reinforcement Learning
- Blog: A trajectory is worth three sentences: multimodal transformer for offline reinforcement learning
- Blog: Learning One Representation to Optimize All Rewards
- Blog: Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery
- Blog: Task and Domain Adaptive Reinforcement Learning for Robot Control
Showing 60 of 69 papers.
History & citation
Current · Permanent link
- This direction split from Decoupling World Dynamics from Task Objectives in Reinforcement Learning (78% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_policy_retraining_overhead_697a8b9c,
title = {policy retraining overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/policy-retraining-overhead/rdr_697a8b9caf394eef96bbe3f135225c70},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_policy_retraining_overhead_697a8b9c_v1,
title = {policy retraining overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/policy-retraining-overhead/rdr_697a8b9caf394eef96bbe3f135225c70/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}