arXiv:2602. 19373v3 Announce Type: replace Abstract: Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data distributions evolve over time.
arXiv:2601. 23075v2 Announce Type: replace Abstract: On-policy Reinforcement Learning (RL) remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy, and policy updates must be conservative.
arXiv:2607.26924v3 Announce Type: replace Abstract: Recent work on LeWorldModel (LeWM) has shown that the Sketched Isotropic Gaussian Regularizer (SIGReg) enables stable end-to-end world model learni...
arXiv:2606. 05888v1 Announce Type: new Abstract: Retry-based objectives such as pass@K and max@K optimize the best return obtained from multiple sampled trajectories, and recent work has shown that they can promote exploration without explicit exploration bonuses.
arXiv:2602. 12643v2 Announce Type: replace-cross Abstract: We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead.
arXiv:2408. 02295v4 Announce Type: replace Abstract: Conventional uncertainty-aware temporal difference (TD) learning often models TD errors as zero-mean Gaussian.
arXiv:2602. 24012v2 Announce Type: replace Abstract: Contrastive learning has become a cornerstone of modern representation learning, allowing training with massive unlabeled data for both task-specific and general (foundation) models.
arXiv:2602. 10430v2 Announce Type: replace-cross Abstract: Off-policy policy optimization reuses historical behavior, including negative-advantage samples that suppress known failures.
Vector Symbolic Policy Gradient (VSPG) is a discrete-action actor that encodes each action as a unit‑norm hypervector and evaluates it by similarity to the encoded state. Its policy‑gradient update reduces to advantage‑weighted hypervector bundling followed by normalization, enabling the use of standard advantage estimators. The learned action hypervectors act as fixed‑size compressed kernel memories that store advantage‑weighted expansions over visited states, allowing evidence transfer via encoder‑induced similarity and providing a robustness guarantee for greedy action selection under random bit flips.
arXiv:2510. 11103v3 Announce Type: replace-cross Abstract: Many robotic control tasks require policies to act on orientations, yet the geometry of SO(3) makes this nontrivial.
arXiv:2510. 13704v2 Announce Type: replace-cross Abstract: Recent works have proposed accelerating the wall-clock training time of actor-critic methods via the use of large-scale environment parallelization; unfortunately, these can sometimes still require large number of environment interactions to achieve a desired level of performance.
arXiv:2608. 06595v1 Announce Type: cross Abstract: Neural networks applied to sequential decision-making tasks typically rely on latent representations of environment states.
arXiv:2606. 03382v1 Announce Type: cross Abstract: While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stationary environments.