andrewschreiber / agent
Interpretability dashboard for reinforcement learners
☆16Updated 5 years ago
Alternatives and similar repositories for agent:
Users that are interested in agent are comparing it to the libraries listed below
- Training (hopefully) safe agents in gridworlds☆25Updated 5 years ago
- A gym environment for Stuart Armstrong's model of a treacherous turn.☆17Updated 6 years ago
- Implementation of https://medium.com/ai-control/alba-an-explicit-proposal-for-aligned-ai-17a55f60bbcf☆27Updated 7 years ago
- ☆12Updated 3 years ago
- Adapting the AlphaZero algorithm to remove the need of execution traces to train NPI.☆79Updated last year
- Progress, Notes, Summaries and a lot of Questions on Machine Learning☆55Updated 5 years ago
- ☆20Updated 5 years ago
- An environment for benchmarking commonsense agents☆28Updated 4 years ago
- Code to reproduce the experiments in The Mirage of Action-Dependent Baselines in Reinforcement Learning.☆17Updated 6 years ago
- Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks☆49Updated 2 years ago
- Explore the optimization landscape for direct policy learning reinforcement learning.☆50Updated 6 years ago
- HOUDINI: Lifelong Learning as Program Synthesis☆48Updated 4 years ago
- ☆9Updated 5 years ago
- Library to compare and evaluate reward functions☆65Updated last year
- Code for the paper, "Learning Human Objectives by Evaluating Hypothetical Behavior"☆83Updated 5 years ago
- Pytorch implementation of LOLA (https://arxiv.org/abs/1709.04326) using DiCE (https://arxiv.org/abs/1802.05098)☆93Updated 6 years ago
- Submissions for AI and Efficiency SOTA's☆56Updated 4 years ago
- Command-line recursive question-answering with immutable contexts and explicit data store☆25Updated 6 years ago
- ☆85Updated 4 years ago
- A Python library for defining flat or nested dictionary flags.☆31Updated last year
- Redwood Research's transformer interpretability tools☆14Updated 2 years ago
- Reward Learning by Simulating the Past☆44Updated 5 years ago
- SafeLife: safety benchmarks for reinforcement learning agents☆60Updated 3 years ago
- A simple moving dot environment for OpenAI Gym to test reinforcement learning algorithms☆22Updated 2 years ago
- Standard interface for entity based reinforcement learning environments.☆36Updated last year
- ☆31Updated 2 years ago
- The first place solution for the NeurIPS 2021 Nethack Challenge -- https://www.aicrowd.com/challenges/neurips-2021-the-nethack-challenge☆59Updated 2 years ago
- ☆20Updated 3 years ago
- This is a pip package implementing Reinforcement Learning algorithms in non-stationary environments supported by the OpenAI Gym toolkit.☆31Updated 5 years ago
- A toy model of Friston's active inference in Tensorflow☆40Updated 7 years ago