Introduces an execution semantics layer for event-driven industrial dispatching that constructs valid decision snapshots, standardizes action admissibility, and attributes multi-level execution divergences to reduce sim-to-real mismatch in RL policies.
Challenges of real- world reinforcement learning,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
GIFT fine-tunes deep RL policies with a stability-focused reward to improve global stability while preserving task performance.
A hybrid DRL system for multi-pair crypto trading with deterministic risk shielding outperforms a heuristic baseline at 10% significance on Binance futures data.
citing papers explorer
-
Bridging the Sim-to-Real Gap in Reinforcement Learning-Based Industrial Dispatching through Execution Semantics
Introduces an execution semantics layer for event-driven industrial dispatching that constructs valid decision snapshots, standardizes action admissibility, and attributes multi-level execution divergences to reduce sim-to-real mismatch in RL policies.
-
GIFT: Global stabilisation via Intrinsic Fine Tuning
GIFT fine-tunes deep RL policies with a stability-focused reward to improve global stability while preserving task performance.
-
Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning
A hybrid DRL system for multi-pair crypto trading with deterministic risk shielding outperforms a heuristic baseline at 10% significance on Binance futures data.