rddl 5 planning 4 tensorflow 4 reinforcement-learning 4 markov-decision-processes 3 python 3 dynamic-programming 3 gym 3 bellman-equation 2 actor-critic 2 gymnasium 2 markov-decision-process 2 sandbox 1 security 1 training-data 1 tool 1 h5 1 dbn 1 epsilon-greedy 1 parser 1 pytorch 1 reward-shaping 1 experience-replay 1 target-network 1 neural-networks 1 deep-learning 1 advantage-function 1 gae 1 generalized-advantage-estimation 1 trust-region 1 model-free 1 off-policy 1 on-policy 1 trpo 1 simulator 1 probabilistic-planning 1 rddl-domains 1 planning-domain-definition-language 1 gym-environments 1 benchmarks 1 benchmarking-suite 1 benchmark-suite 1 stochastic-control 1 neural-dp 1 bellman 1 backward-induction 1 reinforcement-learning-algorithms 1 planning-algorithms 1 agent 1 Reinforcement Learning 1 MDP 1 Markov Decision Process 1 sdk 1 model-drive-protocol 1 mcp 1 client 1 facct 1 antchain 1 value-iteration 1 stochastic 1 optimization 1 operations-research 1 openai-gym 1 rl 1 probability 1 monte-carlo 1 jupyter 1 reward-machine 1 non-markovian 1 simulation 1 drone 1 travelling-thief-problem 1 tsp 1 routing 1 combinatorial-optimization 1 probabilistic-programming 1 logic-programming 1 probabilistic logic programming 1 problog 1 exploration-exploitation 1 policy-network 1 value-function 1 temporal-difference 1 td-learning 1 soft-actor-critic 1 sac 1 ddpg 1 proximal-policy-optimization 1 ppo 1 a3c 1 reinforce 1 policy-gradient 1 deep-q-network 1 dqn 1 q-learning 1 automation 1 data-processing 1 ml 1 ai 1 tools 1