Rollout-level advantage-prioritized experience replay for GRPO recycles high-advantage individual rollouts with age eviction and fresh-anchored batches to outperform standard GRPO on math benchmarks, with gains increasing with model size.
Self-improving reactive agents based on reinforcement learning, planning and teaching
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Eligibility traces in deep RL create a peak bias by amplifying distal TD errors into gradient shocks that fixed-step SGD cannot normalize, leading to overestimation of peak-reward trajectories and a mechanistic account of the peak-end rule.
Artifacts in the environment can reduce the memory an RL agent needs to represent its history, as shown by a mathematical proof and experiments with spatial paths.
CLaaS enables sample-efficient online continual learning for agents via replay-buffered parametric updates, outperforming in-context learning in forward transfer and retention on an adversarial task.
citing papers explorer
-
Trace-Mediated Peak Bias: Bridging Temporal Credit Assignment and Cognitive Heuristics in Deep Reinforcement Learning
Eligibility traces in deep RL create a peak bias by amplifying distal TD errors into gradient shocks that fixed-step SGD cannot normalize, leading to overestimation of peak-reward trajectories and a mechanistic account of the peak-end rule.
-
Artifacts as Memory Beyond the Agent Boundary
Artifacts in the environment can reduce the memory an RL agent needs to represent its history, as shown by a mathematical proof and experiments with spatial paths.
-
CLaaS: Continual learning as a service for sample efficient online learning
CLaaS enables sample-efficient online continual learning for agents via replay-buffered parametric updates, outperforming in-context learning in forward transfer and retention on an adversarial task.