Entity · technique

Twin Delayed DDPG

techniqueactiveprovisionaltwin-delayed-ddpg-8d24e65a·1 events·first seen 2d ago

Aliases: Twin Delayed DDPG

Co-occurring entities

Explainable Reinforcement Learning via Physics-Aware Policy Distillation

More like this (12)

PyTorch DDP DualDPO DDPM DPG Benchmark Multi-Gossip Accelerated DSGD LC-DP DDPO Approximate DP DOPD Parallel Decoding Distillation GDN-2 DPO

Recent events (1)

3arXiv · cs.LG·2d ago·source ↗

Physics-aware policy distillation makes deep RL agents interpretable via decision tree surrogates

A new arXiv preprint presents a policy distillation framework that transfers a high-performance TD3 reinforcement learning agent into a shallow decision tree surrogate for interpretable continuous control, demonstrated on the Inverted Pendulum benchmark. The method uses physics-aware features and 'Noisy Oracle Rollouts' to match teacher performance while providing global and local interpretability. A key finding is a fundamental trade-off: discretizing control induces Bang-Bang actuation and a bimodal limit cycle, though BIBO stability is preserved. The work targets safety-critical deployment contexts where regulatory compliance and human-agent trust require explainability.

AI Safety Research Explainable Reinforcement Learning via Physics-Aware Policy Distillation Twin Delayed DDPG