arXiv:2607. 19397v1 Announce Type: new Abstract: Deep Q-networks use target networks to stabilise bootstrapped value learning, but the standard hard copy update also introduces a tradeoff.
arXiv:2608. 07335v1 Announce Type: cross Abstract: Recent advancements in deep reinforcement learning have increasingly favored simplified, highly parallelized paradigms.
arXiv:2608. 03069v1 Announce Type: new Abstract: Deep Q-Networks (DQNs) learn value functions through bootstrapped temporal-difference updates, where future returns are approximated using a greedy maximization over next-state action values.
arXiv:2606. 29806v1 Announce Type: cross Abstract: Action-values are foundational to many control algorithms such as Q-learning.
arXiv:2607. 27203v1 Announce Type: new Abstract: Pre-training followed by fine-tuning has become the dominant recipe for learning performant policies, and in value-based reinforcement learning (RL) this raises a natural question: given a pretrained policy, should the Q-function be pretrained on offline data too?
arXiv:2511. 03836v2 Announce Type: replace Abstract: Deep Q-Networks (DQNs) estimate future returns by learning from transitions sampled from a replay buffer.
Pre-training followed by fine-tuning has become the dominant recipe for learning performant policies, and in value-based reinforcement learning (RL) this raises a natural question: given a pretrained policy, should the Q-function be pretrained on offline data too? Conventional wisdom suggests it should, but recent results show that online RL with a randomly-initialized Q-function can result in highly performant and reliable policies without needing to pretrain the Q-function.
arXiv:2607. 18722v1 Announce Type: new Abstract: Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but staleness is an inevitable byproduct compounded by policy lag, engine delays, and mixture-of-experts routing.
arXiv:2602. 03120v2 Announce Type: replace-cross Abstract: Post-Training Quantization (PTQ) is essential for deploying Large Language Models (LLMs) on memory-constrained devices, yet it renders models static and difficult to fine-tune.
arXiv:2506. 05716v2 Announce Type: replace-cross Abstract: Deep Q-Networks (DQN) can suffer from overestimation bias because bootstrapped targets use a maximisation operation over noisy value estimates.
Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but staleness is an inevitable byproduct compounded by policy lag, engine delays, and mixture-of-experts routing. From a trust-region perspective, this mismatch is critical: training-inference divergence governs approximation error in finite-horizon bounds, whereas PPO clipping only gates sampled outward updates, acting as a sampled surrogate rather than a full-policy constraint.
arXiv:2605. 22142v2 Announce Type: replace-cross Abstract: Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly model short-term-to-long-term transfer of symbolic observations.
arXiv:2607. 20548v1 Announce Type: cross Abstract: Higher-order optimizers such as Muon and SOAP offer faster convergence than AdamW, but their computational cost and numerical stability challenges have limited adoption at scale.