thiagopbueno / tf-mdp
Probabilistic planning in continuous state-action MDPs in TensorFlow.
☆11Updated 2 years ago
Related projects: ⓘ
- Planning through backpropagation using TensorFlow.☆16Updated 3 years ago
- A toolkit for working with RDDL domains in Python3.☆16Updated 3 years ago
- Code that translates grammar into PDDL, runs a planner to produce multiple plans, translates plans into trainable lale pipelines and trai…☆17Updated last year
- A curated list of online resources for probabilistic planning: papers, software and research groups around the world!☆54Updated 6 years ago
- ☆15Updated 3 years ago
- A Library of MDP algorithms for Artificial Intelligence☆18Updated 5 years ago
- Automatically exported from code.google.com/p/rddlsim☆48Updated 6 months ago
- Code for "Calibrated Model-Based Deep Reinforcement Learning", ICML 2019.☆54Updated 5 years ago
- Datasets for Goal and Plan Recognition using Classical Planning Domains.☆21Updated 5 years ago
- Scalable MCTS for team scenarios☆15Updated 3 months ago
- Code for CORL'18 paper "Risk-Aware Active Inverse Reinforcement Learning"☆15Updated 5 years ago
- A toolkit for auto-generation of OpenAI Gym environments from RDDL description files.☆62Updated last week
- Hierarchical Online Planning and Reinforcement Learning on Taxi☆30Updated 6 years ago
- Non-linear policy graph improvement - planning for Dec-POMDPs☆16Updated 3 years ago
- An algorithm for parsing any planning problem in PDDL format☆17Updated last year
- Easy MDPs and grid worlds with accessible transition dynamics to do exact calculations☆47Updated 2 years ago
- PDDL planner interface for PDDLGym.☆26Updated 7 months ago
- Estimating Q(s,s') with Deep Deterministic Dynamics Gradients☆30Updated 4 years ago
- Infer how suboptimal agents are suboptimal while planning, for example if they are hyperbolic time discounters.☆22Updated 3 years ago
- Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play☆14Updated 6 years ago
- (Experimental) Inverse reinforcement learning from trajectories generated by multiple agents with different (but correlated) rewards☆25Updated 5 years ago
- A comparison of parameter space noise methods for exploration in deep reinforcement learning☆28Updated 5 years ago
- probabilistic planning system for tasks encoded in RDDL☆37Updated last year
- ☆20Updated 5 months ago
- Comp 781 Project☆8Updated 5 years ago
- Source for Action Schema Networks paper (AAAI'18)☆29Updated last year
- Implementation of the skill discovery algorithm described in ICLR submission "Option Discovery using Deep Skill Chaining"☆28Updated 4 years ago
- This repository contains the code used in the paper Evaluating the Performance of Reinformcent Learning Algorithms☆27Updated 3 years ago
- Reinforcement Learning for Classical Planning☆10Updated 2 years ago
- IRL Toolkit developed by Sergey Levine (Taken from https://graphics.stanford.edu/projects/gpirl/)☆62Updated 7 years ago