Deep RL Algorithms in Cryptocurrency Trading
Built an ETH trading environment (continuous state/action) with trading features and actions through hourly Bitfinex ETH dataset. Re-implemented and debugged off-policy actor-critic agents (DDPG, TD3, SAC) with replay/target networks; benchmarked against random walk trading policy and found SAC achieved the best returns while TD3 trained more stably than DDPG.