IBM / vsrl-frameworkLinks
The Verifiably Safe Reinforcement Learning Framework
☆57Updated 4 years ago
Alternatives and similar repositories for vsrl-framework
Users that are interested in vsrl-framework are comparing it to the libraries listed below
Sorting:
- Learning algorithm implementation and experiments in the paper "A Composable Specification Language for Reinforcement Learning Tasks" (ht…☆17Updated 4 years ago
- ☆44Updated 2 years ago
- Reachability Analysis Tool of Neural Network Controlled Systems (NNCSs)☆17Updated 2 years ago
- Reinforcement Learning framework for Temporal Goals☆11Updated 2 years ago
- ☆71Updated last year
- ☆18Updated 2 years ago
- Logically-Constrained Reinforcement Learning☆54Updated last year
- Code for experiments in the paper: "Compositional Reinforcement Learning from Logical Specifications" (https://arxiv.org/abs/2106.13906).☆16Updated 4 years ago
- Safe Reinforcement Learning algorithms☆75Updated 3 years ago
- Repository containing the PhD Thesis "Formal Verification of Deep Reinforcement Learning Agents"☆10Updated 3 years ago
- Implementation of the Model-Based Meta-Policy-Optimization (MB-MPO) algorithm☆44Updated 6 years ago
- ☆24Updated 3 years ago
- Sherlock is a tool for output range anaylsis of Deep Neural Networks with ReLU activation units.☆30Updated 5 years ago
- Code that translates grammar into PDDL, runs a planner to produce multiple plans, translates plans into trainable lale pipelines and trai…☆18Updated last month
- DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning☆23Updated 4 years ago
- Python library for working with Metric Temporal Logic (MTL)☆101Updated 2 years ago
- Neurosymbolic transformers for multi-agent communication.☆22Updated 5 years ago
- From LTLf / PPLTL to Deterministic Finite-state Automata (DFA)☆73Updated last year
- Source for Action Schema Networks paper (AAAI'18)☆32Updated 2 years ago
- ☆14Updated 3 months ago
- Safe exploration in Markov Decision Processes☆37Updated 7 years ago
- Easy MDPs and grid worlds with accessible transition dynamics to do exact calculations☆49Updated 3 years ago
- Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks☆51Updated 2 years ago
- Open source demo for the paper Learning to Score Behaviors for Guided Policy Optimization☆24Updated 5 years ago
- LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization☆37Updated 2 years ago
- Safe Model-based Reinforcement Learning with Robust Cross-Entropy Method☆66Updated 2 years ago
- ☆32Updated last year
- ☆10Updated 2 years ago
- Implementation and evaluation of Almanac (Automaton/Logic Multi-Agent Natural Actor-Critic), an algorithm for multi-agent reinforcement l…☆10Updated 3 years ago
- Code for the paper "AlwaysSafe: Reinforcement Learning Without Safety Constraint Violations During Training"☆17Updated 3 years ago