#deep-reinforcement-learning

[ follow ]
#transaction-costs

Evaluating Deep RL Agents in Hedging with Market-Calibrated Stochastic Volatility Models | HackerNoon

DRL agents outperform BS Delta strategies in hedging performance, particularly under transaction costs.

Results of Deep Reinforcement Learning Agent Performance in Hedging American Put Options | HackerNoon

The effectiveness of a DRL agent depends significantly on transaction costs and market conditions.

Evaluating Deep RL Agents in Hedging with Market-Calibrated Stochastic Volatility Models | HackerNoon

DRL agents outperform BS Delta strategies in hedging performance, particularly under transaction costs.

Results of Deep Reinforcement Learning Agent Performance in Hedging American Put Options | HackerNoon

The effectiveness of a DRL agent depends significantly on transaction costs and market conditions.
moretransaction-costs
#stochastic-volatility

Advancements in Deep Reinforcement Learning for Hedging American Put Options | HackerNoon

The article introduces DRL agents for hedging American put options, enhancing existing methodologies in the field.

Hedging American Put Options with Deep Reinforcement Learning: Training Procedures | HackerNoon

Robust asset data generation and reward structure are essential for training DRL agents in hedging American put options.

Advancements in Deep Reinforcement Learning for Hedging American Put Options | HackerNoon

The article introduces DRL agents for hedging American put options, enhancing existing methodologies in the field.

Hedging American Put Options with Deep Reinforcement Learning: Training Procedures | HackerNoon

Robust asset data generation and reward structure are essential for training DRL agents in hedging American put options.
morestochastic-volatility

Addendum: A graph placement methodology for fast chip design - Nature

AlphaChip represents a significant advancement in AI for engineering, offering enhanced chip layout generation through deep reinforcement learning.

Generative AI that imitates human motion

Researchers have developed a method combining central pattern generators and deep reinforcement learning for robots to imitate human walking and running motions effectively.

Trotting robots reveal emergence of animal gait transitions

EPFL robot learns pronking via DRL to navigate gaps, shedding light on gait transitions due to fall avoidance, not just energy efficiency.
[ Load more ]