niksaz / dota2-expert-demo
Dota 2 bot that is trained by Deep RL with expert demonstrations
☆30Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for dota2-expert-demo
- A platform for intelligent agent learning based on a 3D open-world FPS game developed by Inspir.AI.☆56Updated 2 years ago
- Deep Reinforcement Learning for Multiplayer Online Battle Arena☆74Updated last year
- Baselines for Neural MMO -- new users should treat this repo as a starter project☆46Updated 3 months ago
- The source code for the gym-microrts paper.☆42Updated 2 years ago
- Framework for inspecting actions and observatinos in StarCraftII replays☆20Updated 6 years ago
- ☆21Updated 2 years ago
- StarCraft 2 Imitation Learning☆29Updated 3 years ago
- This is the source code of RPG (Reward-Randomized Policy Gradient)☆43Updated 2 years ago
- Implement IMPALA architecture from Distributed Deep-RL Paper.☆15Updated 6 years ago
- Deep reinforcement learning implementation that trains AIs for the CodeCraft real-time strategy game.☆19Updated last year
- ☆135Updated 3 years ago
- This project is implementation code of AlphaStar☆187Updated 9 months ago
- RL environment replicating the werewolf game to study emergent communication☆18Updated last year
- Fast and procedurally generated side-scroller-game-like graphical environments (formerly Procgen)☆27Updated last year
- (AAAI'2019) The codes, models, logs, and data for an extended paper of the original paper "On Reinforcement Learning for Full-length Game…☆21Updated 2 years ago
- Behavioural cloning experiments with video games☆30Updated 4 years ago
- Gym wrapper for pysc2☆10Updated 2 years ago
- Train an agent to play VizDoom with multi sensory inputs. Trained using sample factory☆14Updated 3 years ago
- World Models with A3C on Carracing-v0 in gym☆32Updated 4 years ago
- [NeurIPS 2022] Open source code for reusing prior computational work in RL.☆91Updated last year
- ☆29Updated last year
- An implementation of MuZero in JAX.☆53Updated 2 years ago
- Code for the paper "Batch size invariance for policy optimization"☆47Updated last year
- A number of agents (PPO, MuZero) with a Perceiver-based NN architecture that can be trained to achieve goals in nethack/minihack environm…☆39Updated 2 years ago
- A2C is a special case of PPO!☆19Updated 2 years ago
- ☆80Updated 4 months ago
- A simple and highly efficient RTS-game-inspired environment for reinforcement learning (formerly Gym-MicroRTS)☆232Updated 4 months ago
- Curiosity-driven Exploration by Self-supervised Prediction☆134Updated last year
- implementation of distributed reinforcement learning with distributed tensorflow☆57Updated 3 years ago
- TeachMyAgent is a testbed platform for Automatic Curriculum Learning methods in Deep RL.☆66Updated 11 months ago