brownirl / lambda_discrepancy
Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy
☆17Updated 5 months ago
Alternatives and similar repositories for lambda_discrepancy:
Users that are interested in lambda_discrepancy are comparing it to the libraries listed below
- POPGym Library in JAX☆11Updated 11 months ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆50Updated last year
- ☆20Updated 9 months ago
- SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning☆14Updated 2 years ago
- ☆18Updated 2 months ago
- Official implementation of the δ-model presented in the ICML 2024 paper "A Distributional Analogue to the Successor Representation".☆20Updated 4 months ago
- Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"☆22Updated last year
- Accelerated replay buffers in JAX☆41Updated 2 years ago
- Contains JAX implementation of algorithms for inverse reinforcement learning☆71Updated 7 months ago
- Scalable Opponent Shaping Experiments in JAX☆24Updated 11 months ago
- Code for Discovered Policy Optimisation (NeurIPS 2022)☆9Updated last year
- ☆13Updated 8 months ago
- ☆10Updated 9 months ago
- Conservative Q learning in Jax☆53Updated 2 years ago
- ☆35Updated 2 years ago
- ☆75Updated 2 weeks ago
- A collection of matrix games in JAX☆10Updated 4 months ago
- Novelty MiniGrid--NovGrid--is an extension of MiniGrid environment that allows for the world properties and dynamics to change according …☆35Updated 10 months ago
- Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"☆22Updated 4 months ago
- Learning diverse options through the Laplacian representation.☆23Updated last year
- Code for the papers Hypernetworks in Meta-Reinforcement Learning (Beck et al., 2022) and Recurrent Hypernetworks are Surprisingly Strong …☆12Updated 8 months ago
- ☆47Updated 2 years ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆53Updated 2 years ago
- Rainbow DQN implementation accompanying the paper "Fast and Data-Efficient Training of Rainbow" which reaches 205.7 median HNS after 10M …☆44Updated 3 years ago
- Sandbox environment for generalizable agent research☆24Updated 2 years ago
- Docker containers of baseline agents for the Crafter environment☆28Updated 3 years ago
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]☆99Updated last year
- An Open-Ended Agentic Simulator☆45Updated 7 months ago
- Official codebase for Generating Diverse Cooperative Agents by Learning Incompatible Policies (notable-top-25% @ ICLR 2023)☆16Updated 10 months ago
- Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"☆45Updated 9 months ago