Honor mode has me Ripping my hair out 😂 (Im gonna beat it one day)
How cooked is bro?
RL Agent: DQN and Doubel DQN not Converging in the LunarLander environment
New Player, need help in Witcher 3
Soft action masking
I’m so lost, can’t get to sunny shore city
Do I replace any with Giratina? Or is it going to make the game too easy? I'm no expert of the Pokemon games, just a casual fan. Also any advice on the team is welcomed!
Future Archeologists
What is the "black box" element in NNs?
What is the most complex environment in which RL agents currently perform optimally without incentivizing specific behaviours?
Hybrid Action Space Implementations
Question on offline RL
Help Request: Struggling with Improving AI Performance in Dungeon Navigation Project
I don't think HM is for me...
How do optimistic initial values encourage exploration?
Question about RL agents controlling other RL agents
TD3 reward not increasing over time
Is categorical DQN useful for deterministic fully observed environnments
question about TD3
I feel like it's a little much that I can make 8-9 summons
Question on convergence of DQN and its variants
Recommendations for transfer RL papers?
Monopoly reinforcement learning project
SAC for Hybrid Action Space
Give me your ideal Myrkul setup.
