Popular repositories Loading
-
HPB-agent-architecture
HPB-agent-architecture PublicAn agent architecture for controlling an autonomous agent in stochastic, noisy environments. The architecture combines the partially observable Markov decision process (POMDP) model with the belief…
Python
-
LearningMealyRewardMachines
LearningMealyRewardMachines PublicCode for the framework which learns reward models with temporal dependencies. The associated publication is Rens et al. (2021) Online Learning of Non-Markovian Reward Models
Python
-
Vanilla_Online_POMDP
Vanilla_Online_POMDP PublicA simple POMDP planner for online planning from a given belief state. No pruning or any optimization is applied. Can be used for only very small environments.
Python< 41EA /span>
-
Reward-Machine-Agent---Treasure-Hunting
Reward-Machine-Agent---Treasure-Hunting PublicA treasure-hunting agent controlled by a MCTS planner using a Reward Machine.
ShaderLab
-
Reward-Machine-Agent---Patrolling
Reward-Machine-Agent---Patrolling PublicA patrolling agent controlled by a MCTS planner using a Reward Machine, capable of dealing with non-deterministic observations.
ShaderLab
-
Hybrid-Agent---Work-n-Home
Hybrid-Agent---Work-n-Home PublicAn agent architecture combining the HMB and NRMDP architectures.
ShaderLab
If the problem persists, check the GitHub status page or contact support.