Deep hedging agents learn a systematic delta haircut explained by spot-implied-volatility co-movement; symbolic regression distills the policies into formulas that retain reward and downside-variance advantages over Black-Scholes but inherit regime fragility.
hub Canonical reference
Policy distillation
Canonical reference. 80% of citing Pith papers cite this work as background.
18
Pith papers citing it
Background
80% of classified citations
abstract
Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve good performance. In this work, we present a novel method called policy distillation that can be used to extract the policy of a reinforcement learning agent and train a new network that performs at the expert level while being dramatically smaller and more efficient. Furthermore, the same method can be used to consolidate multiple task-specific policies into a single policy. We demonstrate these claims using the Atari domain and show that the multi-task distilled agent outperforms the single-task teachers as well as a jointly-trained DQN agent.
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
representative citing papers
SafeAdapt certifies a Rashomon set of safe policies from demonstration data and projects updates from arbitrary RL algorithms onto it to guarantee preservation of safety on source tasks.
OPD for LLMs suffers length inflation and repetition collapse; StableOPD uses reference divergence and rollout mixing to prevent it and improve math reasoning performance by 7.2% on average.
Policy-DRIFT combines conditional flow matching with terminal reward guidance and decoupled DRL to achieve 49% drag reduction in Re_tau=180 channel flow, 16% above DRL benchmarks and with 37 times less actuation energy.
Process advantage verifiers trained to predict step-level progress under a distinct prover policy improve LLM reasoning accuracy by over 8% and sample efficiency by 5-6x over outcome reward models.
Continual Domain Randomization trains RL policies sequentially on randomization parameter subsets with continual learning to achieve robust sim-to-real transfer in robotic reaching and grasping.
Attention mechanism dynamically groups task knowledge at state granularity in multi-task DRL to enable positive transfer and avoid negative transfer, matching or exceeding prior methods with fewer parameters.
DeRAN converts black-box DRL policies into interpretable symbolic representations for O-RAN automation, retaining 78-87% of original performance while adding built-in transparency.
Reinforcement learning sensorimotor policies enable quadrotors to traverse narrow gaps at extreme tilts with 5 cm clearance using only vision and proprioception, including reactive traversal of moving gaps.
MiniLLM distills large language models into smaller ones via reverse KL divergence and on-policy optimization, yielding higher-quality responses with lower exposure bias than standard KD baselines.
Progressive neural networks learn sequences of RL tasks without catastrophic forgetting by freezing prior columns and adding lateral connections for knowledge transfer.
A teacher-student RL policy distillation approach combined with procedural tunnel generation enables quadruped robots to traverse narrow tunnels consistently in both simulation and real-world tests.
VISD proposes structured self-distillation with a multi-dimensional judge model and direction-magnitude decoupling to improve token-level credit assignment and convergence speed in VideoLLM reasoning training.
LANTERN improves RL sample efficiency by 40-60% via LLM-generated task automata, semantic multi-source policy aggregation, and experience-gated adaptive transfer.
A review of 15 studies finds positive transfer in DRL mainly when source and target tasks share structure or include alignment mechanisms, but compute-matched comparisons against from-scratch baselines remain rare.
JEPA-Indexed Local Expert Growth adds local action corrections for detected shift clusters and yields statistically significant OOD gains on four shift conditions while keeping in-distribution performance intact.
ReFineVLA adds teacher-generated reasoning steps to VLA training and reports state-of-the-art success rates on SimplerEnv WidowX and Google Robot benchmarks.
A survey frames CPS resilience through five themes and illustrates them in connected transportation and medical systems to provide a roadmap for real-world resilience.
citing papers explorer
-
What Does Deep Hedging Actually Learn? Delta Corrections, Regime Fragility, and Symbolic Distillation
Deep hedging agents learn a systematic delta haircut explained by spot-implied-volatility co-movement; symbolic regression distills the policies into formulas that retain reward and downside-variance advantages over Black-Scholes but inherit regime fragility.
-
SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning
SafeAdapt certifies a Rashomon set of safe policies from demonstration data and projects updates from arbitrary RL algorithms onto it to guarantee preservation of safety on source tasks.
-
Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models
OPD for LLMs suffers length inflation and repetition collapse; StableOPD uses reference divergence and rollout mixing to prevent it and improve math reasoning performance by 7.2% on average.
-
Policy-DRIFT: Dynamic Reward-Informed Flow Trajectory Steering
Policy-DRIFT combines conditional flow matching with terminal reward guidance and decoupled DRL to achieve 49% drag reduction in Re_tau=180 channel flow, 16% above DRL benchmarks and with 37 times less actuation energy.
-
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
Process advantage verifiers trained to predict step-level progress under a distinct prover policy improve LLM reasoning accuracy by over 8% and sample efficiency by 5-6x over outcome reward models.
-
Continual Domain Randomization
Continual Domain Randomization trains RL policies sequentially on randomization parameter subsets with continual learning to achieve robust sim-to-real transfer in robotic reaching and grasping.
-
Attentive Multi-Task Deep Reinforcement Learning
Attention mechanism dynamically groups task knowledge at state granularity in multi-task DRL to enable positive transfer and avoid negative transfer, matching or exceeding prior methods with fewer parameters.
-
Demystifying Deep Reinforcement Learning: A Neuro-Symbolic Framework for Interpretable Open RAN Automation
DeRAN converts black-box DRL policies into interpretable symbolic representations for O-RAN automation, retaining 78-87% of original performance while adding built-in transparency.
-
Precise Aggressive Aerial Maneuvers with Sensorimotor Policies
Reinforcement learning sensorimotor policies enable quadrotors to traverse narrow gaps at extreme tilts with 5 cm clearance using only vision and proprioception, including reactive traversal of moving gaps.
-
MiniLLM: On-Policy Distillation of Large Language Models
MiniLLM distills large language models into smaller ones via reverse KL divergence and on-policy optimization, yielding higher-quality responses with lower exposure bias than standard KD baselines.
-
Progressive Neural Networks
Progressive neural networks learn sequences of RL tasks without catastrophic forgetting by freezing prior columns and adding lateral connections for knowledge transfer.
-
Robot Squid Game: Quadrupedal Locomotion for Traversing Narrow Tunnels
A teacher-student RL policy distillation approach combined with procedural tunnel generation enables quadruped robots to traverse narrow tunnels consistently in both simulation and real-world tests.
-
VISD: Enhancing Video Reasoning via Structured Self-Distillation
VISD proposes structured self-distillation with a multi-dimensional judge model and direction-magnitude decoupling to improve token-level credit assignment and convergence speed in VideoLLM reasoning training.
-
LANTERN: LLM-Augmented Neurosymbolic Transfer with Experience-Gated Reasoning Networks
LANTERN improves RL sample efficiency by 40-60% via LLM-generated task automata, semantic multi-source policy aggregation, and experience-gated adaptive transfer.
-
Combining Trained Models in Reinforcement Learning
A review of 15 studies finds positive transfer in DRL mainly when source and target tasks share structure or include alignment mechanisms, but compute-matched comparisons against from-scratch baselines remain rare.
-
Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift
JEPA-Indexed Local Expert Growth adds local action corrections for detected shift clusters and yields statistically significant OOD gains on four shift conditions while keeping in-distribution performance intact.
-
ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning
ReFineVLA adds teacher-generated reasoning steps to VLA training and reports state-of-the-art success rates on SimplerEnv WidowX and Google Robot benchmarks.
-
Digital Guardians: The Past and The Future of Cyber-Physical Resilience
A survey frames CPS resilience through five themes and illustrates them in connected transportation and medical systems to provide a roadmap for real-world resilience.