Goal-oriented Trajectories for Efficient Exploration
🔍 Exploration (episode 300)
🔍 Exploration (episode 300)
DQN with epsilon-greedy exploration
DQN with epsilon-greedy exploration
DQN with Q-map exploration
DQN with Q-map exploration
🚩 First flag
🚩 First flag
DQN with epsilon-greedy exploration
DQN with epsilon-greedy exploration
DQN with Q-map exploration
DQN with Q-map exploration
🏆 Highest score (with flag)
🏆 Highest score (with flag)
DQN with epsilon-greedy exploration
DQN with epsilon-greedy exploration
DQN with Q-map exploration
DQN with Q-map exploration
📈 Results
📈 Results
Random walk (red) and Q-map walk (green)
Random walk (red) and Q-map walk (green)
DQN with epsilon-greedy (red) and DQN with Q-map (green)
DQN with epsilon-greedy (red) and DQN with Q-map (green)
Performance comparison
Performance comparison
