The paper introduces temporally interpretable differentiable decision trees (DDTs) that incorporate action chunking to better align tree-based decision making with multi‑timestep planning. Two new policy‑gradient algorithms and an information‑theoretic tree‑restructuring method are proposed to enable efficient training of these trees. Experiments on four simulation environments show that warm‑starting action‑chunked DDTs from a distilled policy yields trees that match neural network performance in three domains while using up to 80% fewer parameters.
Interpretability offers a solution to safe autonomy by providing transparency into an agent's underlying decision-making model. Within sequential-decision making tasks, differentiable decision trees (...
arXiv:2608. 07151v1 Announce Type: cross Abstract: Reinforcement learning policies are difficult to inspect, but interpreting them is a prerequisite for trustworthiness.
arXiv:2607. 07235v1 Announce Type: cross Abstract: Explainability remains a key issue in reinforcement learning (RL).
arXiv:2609.36471v1 Announce Type: cross Abstract: World-Action Models (WAMs) improve robotic manipulation by conditioning action generation on predicted future observations, but future prediction add...
arXiv:2606. 08596v1 Announce Type: new Abstract: Constructing efficient and reliable policies to assist humans is indispensable for human-AI collaboration.
arXiv:2602. 14265v3 Announce Type: replace-cross Abstract: Inference-Time-Compute (ITC) methods like Best-of-$n$ and Tree-of-Thoughts are meant to produce output candidates that are both high-quality and diverse, but their use of high-temperature sampling often fails to achieve meaningful output diversity.
arXiv:2608. 07581v1 Announce Type: cross Abstract: Group-based reinforcement learning methods for multimodal large language models typically rely on trajectory-level credit assignment that applies a single advantage to all tokens in a response.
arXiv:2608.30640v1 Announce Type: new Abstract: While self-supervised approaches to reinforcement learning have achieved strong results by learning representations of states and actions, a key open q...
Large language model (LLM) agents for long-horizon interactive tasks typically follow a ReAct-style protocol, issuing one primitive action per LLM round. While this enables frequent replanning, it is...
arXiv:2606. 04634v1 Announce Type: new Abstract: Trust in a decision-making system requires both safety guarantees and the ability to interpret and understand its behavior.
The paper introduces SPACE, a method for enabling large language model agents to emit variable-length action chunks in long-horizon tasks. By distilling chunk-boundary supervision from programmatic skills derived from successful trajectories, SPACE overcomes the tendency of agents to either act one step at a time or commit to overly long sequences. Experiments on ALFWorld and ScienceWorld demonstrate that SPACE raises success rates by 7.0%–31.3% and cuts LLM decision rounds by up to 78.9%.
The paper introduces the Dual-Latent World Model (Dual-WM), which separates local execution and long-range planning into distinct latent spaces and dynamics models. A new learning method, Long-Horizon Representation Learning with Weighted Rollout (LoRe), supervises predictions at both levels using exponential horizon weights. Experiments on five goal-conditioned visual control tasks show that Dual-WM improves success rates over strong baselines, especially at longer horizons.