CS 4267: Deep Learning Final Project
Source: CartPole-v0 defines "solving" as getting average reward of 195.0 over 100 consecutive trials.
Comparative analysis of DRL algorithms on control theory environments.
CS 4267: Deep Learning Final Project
Source: CartPole-v0 defines "solving" as getting average reward of 195.0 over 100 consecutive trials.
Comparative analysis of DRL algorithms on control theory environments.