rl-toolkit 3.2.5

The RL-Toolkit: A toolkit for developing and comparing your reinforcement learning agents in various games (OpenAI Gym or Pybullet).

RL Toolkit

Papers

• Soft Actor-Critic
• Generalized State-Dependent Exploration
• Reverb: A framework for experience replay
• Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics

Setting up container

# Preview
docker pull markub3327/rl-toolkit:latest

# Stable
docker pull markub3327/rl-toolkit:2.0.2

Run

# Run learner's container
docker run -p 8000:8000 -it --rm markub3327/rl-toolkit

# Run tester's or agent's container
docker run -it --rm markub3327/rl-toolkit


# Learner container
python3 -m rl_toolkit -e [ENV_NAME] learner --db_server [IP_ADDRESS/HOSTNAME] -s [PATH_TO_MODEL] [--wandb] [-h]

# Agent container
python3 -m rl_toolkit -e [ENV_NAME] agent --db_server [IP_ADDRESS/HOSTNAME] [--wandb] [-h]

# Tester container
python3 -m rl_toolkit -e [ENV_NAME] tester --model_path [PATH_TO_MODEL] [--render] [--wandb] [-h]

Tested environments

Environment	Observation space	Observation bounds	Action space	Action bounds
BipedalWalkerHardcore-v3	(24, )	[-inf, inf]	(4, )	[-1.0, 1.0]
Walker2DBulletEnv-v0	(22, )	[-inf, inf]	(6, )	[-1.0, 1.0]
AntBulletEnv-v0	(28, )	[-inf, inf]	(8, )	[-1.0, 1.0]
HalfCheetahBulletEnv-v0	(26, )	[-inf, inf]	(6, )	[-1.0, 1.0]
HopperBulletEnv-v0	(15, )	[-inf, inf]	(3, )	[-1.0, 1.0]
HumanoidBulletEnv-v0	(44, )	[-inf, inf]	(17, )	[-1.0, 1.0]
MinitaurBulletEnv-v0	(28, )	[-167.72488, 167.72488]	(8, )	[-1.0, 1.0]

Results

Summary

Score

Environment	SAC + gSDE	SAC + gSDE + Huber loss	TQC + gSDE	TQC + gSDE + Reverb
BipedalWalkerHardcore-v3	13 ± 18(2)	-	228 ± 18(2)	-
Walker2DBulletEnv-v0	2270 ± 28(1)	2732 ± 96	2535 ± 94(2)	-
AntBulletEnv-v0	3106 ± 61(1)	3460 ± 119	3700 ± 37(2)	-
HalfCheetahBulletEnv-v0	2945 ± 95(1)	3003 ± 226	3041 ± 157(2)	-
HopperBulletEnv-v0	2515 ± 50(1)	2555 ± 405	2401 ± 62(2)	-
HumanoidBulletEnv-v0	-	-	-	-
MinitaurBulletEnv-v0	-	-	-	-

Model

---

Frameworks: Tensorflow, Reverb, OpenAI Gym, PyBullet, WanDB, OpenCV

Changes

v3.2.4 (July 7, 2021)

Features 🔊

• Reverb
• setup.py (package is available on PyPI)
• split into agent, learner and tester roles
• Use custom model and layer for defining Actor-Critic
• MultiCritic - concatenating multiple critic networks into one network
• Truncated Quantile Critics

v2.0.2 (May 23, 2021)

Bug fixes 🛠️

• update Dockerfile
• update README.md
• formatted code by Black & Flake8

v2.0.1 (April 27, 2021)

Bug fixes 🛠️

• fix Critic model

v2.0.0 (April 22, 2021)

Features 🔊

• Add Huber loss
• In test mode, rendering to the video file
• Normalized observation by Min-max method
• Remove TD3 algorithm