policy-gradient

Tag

Cards List
#policy-gradient

Boundary-Seeking Policy Gradient for Safe Reinforcement Learning

arXiv cs.LG · yesterday Cached

Introduces Boundary-Seeking Policy Gradient (BSPG), a first-order method for safe reinforcement learning that actively drives the policy toward the constraint boundary, with convergence guarantees and improved reward/boundary tracking on a Safety-Gymnasium task.

0 favorites 0 likes
#policy-gradient

Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning

arXiv cs.LG · 2026-08-04 Cached

This paper proves that using error-penalized scoring rules with abstention as a discrete action can kill both the reward gradient and the KL anchor, causing models to collapse toward refusing everything. It proposes a structural repair — training a mandatory confidence report — and validates the mechanism with simulations and language model experiments.

0 favorites 0 likes
#policy-gradient

Policy Gradient Steering: Interventions from Behavioral Objectives

arXiv cs.LG · 2026-07-31 Cached

Introduces Policy Gradient Steering (PGS), a method that formulates activation steering as a reinforcement learning problem, using policy gradients to construct removable, composable steering vectors from behavioral objectives. Validated in gridworld, chess puzzle, and football environments.

0 favorites 0 likes
#policy-gradient

From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training

arXiv cs.LG · 2026-07-21 Cached

Introduces Hindsight Policy Optimization (HPO), a novel policy gradient method that uses an intent space and Wasserstein distance to reduce variance in long-horizon language agent training, showing improved stability over GRPO and PPO.

0 favorites 0 likes
#policy-gradient

SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions

arXiv cs.LG · 2026-07-13 Cached

SafeExplorer introduces an unbiased policy gradient estimator for reinforcement learning with recovery interventions, significantly reducing training-time falls on robot tasks while matching or exceeding standard PPO's final reward.

0 favorites 0 likes
#policy-gradient

Predictive Divergence Masks for LLM RL

Hugging Face Daily Papers · 2026-07-12 Cached

Proposes predictive divergence masks for LLM reinforcement learning that improve upon PPO's direction criterion by predicting whether the next policy gradient step will increase or decrease the divergence used by the trust region, leading to better alignment and improved RL training across model scales.

0 favorites 0 likes
#policy-gradient

Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL

arXiv cs.LG · 2026-07-03 Cached

This paper introduces FADE (Focal Advantage with Dynamic Entropy), a self-adapting advantage function that dynamically schedules gradient weights during RL post-training of LLMs, achieving faster convergence and better accuracy-diversity trade-offs compared to static baselines.

0 favorites 0 likes
#policy-gradient

EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games

arXiv cs.LG · 2026-06-24 Cached

EMAgnet introduces parameter-space exponential moving average regularization for policy gradient self-play in large two-player zero-sum games, achieving lower exploitability compared to uniform regularization targets.

0 favorites 0 likes
#policy-gradient

KLip-PPO: A per-sample KL perspective on PPO-Clip

arXiv cs.LG · 2026-06-24 Cached

This paper shows that the gradient of the clipped surrogate in Proximal Policy Optimization (PPO) is exactly reproduced by a per-sample Kullback-Leibler penalty with a variable coefficient, revealing structural features of the clipped surrogate and suggesting new design directions.

0 favorites 0 likes
#policy-gradient

In game theory, generalists sometimes win out over specialists

MIT News — Artificial Intelligence · 2026-06-17 Cached

MIT researchers co-authored a paper showing that general-purpose policy gradient algorithms can outperform specialized game-theoretic algorithms in imperfect-information games, challenging long-held assumptions in the field.

0 favorites 0 likes
#policy-gradient

Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts

arXiv cs.LG · 2026-06-16 Cached

This paper formalizes embedding model routing as an adversarial contextual linear bandit with low-rank experts, proposing the Hypentropy Policy Gradient (HPG) algorithm that achieves O~(s√(MT)) policy regret, avoiding the curse of dimensionality.

0 favorites 0 likes
#policy-gradient

Diffusion Policy Optimization without Drifting Apart

arXiv cs.LG · 2026-06-15 Cached

DiPOD stabilizes diffusion policy optimization by interleaving self-distillation with policy-gradient updates to maintain a tight ELBO, preventing the double-drift phenomenon and achieving higher rewards in both language and continuous control tasks.

0 favorites 0 likes
#policy-gradient

Self-Distilled Policy Gradient

arXiv cs.LG · 2026-06-04 Cached

SDPG (Self-Distilled Policy Gradient) is a new RL training framework for LLMs that combines group-relative verifier advantages with on-policy self-distillation and KL regularization to address sparse rewards and instability in RLVR training. The method uses a shared model as both student and teacher by conditioning on privileged context, showing improved stability and performance over RLVR and self-distillation baselines.

0 favorites 0 likes
#policy-gradient

Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying

arXiv cs.LG · 2026-06-02 Cached

This paper introduces ReMax, a new objective for reinforcement learning that induces exploration as an emergent property by evaluating policies based on expected maximum return over multiple samples, without explicit exploration bonuses. The authors derive a policy gradient formulation and propose RePPO, a PPO variant that achieves efficient exploration on MinAtar and Craftax benchmarks.

0 favorites 0 likes
#policy-gradient

Self-Distilled Policy Gradient

Hugging Face Daily Papers · 2026-06-02 Cached

This paper proposes SDPG, a self-distilled policy-gradient framework that combines on-policy self-distillation with verifier advantages and KL regularization to improve reinforcement learning stability and performance.

0 favorites 0 likes
#policy-gradient

Completion vs Optimality: Policy Gradient in Long-Horizon Cumulative-Damage Problems

arXiv cs.AI · 2026-05-27 Cached

This paper identifies two failure modes for policy-gradient methods in long-horizon cumulative-damage problems—completion and optimality—and proposes a decomposition to address them separately, validated on two calibrated environments.

0 favorites 0 likes
#policy-gradient

Refined Analysis of Entropy-Regularized Actor-Critic

arXiv cs.LG · 2026-05-26 Cached

This paper provides a refined theoretical analysis of actor-critic methods with entropy regularization, showing that an exact critic acts as a strong variance reducer and enables sample complexity comparable to deterministic policy gradient, and that with a sufficiently accurate learned critic the benefits are preserved.

0 favorites 0 likes
#policy-gradient

ECHO: Terminal Agents Learn World Models for Free

Hugging Face Daily Papers · 2026-05-23 Cached

ECHO introduces a hybrid objective that combines policy-gradient loss with environment observation prediction to provide dense supervision from terminal feedback, doubling performance on TerminalBench-2.0 for Qwen3 models.

0 favorites 0 likes
#policy-gradient

Representation over Routing: Overcoming Surrogate Hacking in Multi-Timescale PPO

Hugging Face Daily Papers · 2026-05-21 Cached

This paper identifies surrogate hacking and temporal uncertainty as failure modes in multi-timescale RL, and proposes a Target Decoupling architecture that removes routing from the actor, using the critic for auxiliary representation learning. The method eliminates policy collapse on the LunarLander-v2 benchmark and stably surpasses the 'Environment Solved' threshold without hyperparameter hacking.

0 favorites 0 likes
#policy-gradient

DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards

Hugging Face Daily Papers · 2026-05-20 Cached

Introduces DelTA, a discriminative token credit assignment method for reinforcement learning from verifiable rewards (RLVR) that amplifies distinctive token-gradient directions and reduces noise from shared patterns, achieving significant improvements on mathematical and code generation benchmarks.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback